Progress 09/01/23 to 08/31/24
Outputs
Target Audience: Students (K-12, associate degree programs, undergraduate, graduate) Postdoctoral researchers Faculty at all AgAID member organizations External research collaborators in academia and industry Specialty crop growers Specialty crop agricultural farm managers and workers Crop commissions and crop consultants Water irrigation districts State departments of agriculture and ecology K-12 educators Associate degree program and undergraduate program educators IT industry partners AgTech and FarmTech industry partners Federal funding agencies including USDA NIFA and NSF Population groups: Underrepresented minority groups including (but not limited to) Hispanic/Latinx and Native American First generation college students Underrepresented genders Changes/Problems:There has been no change in the scope or objectives of the project, and in Year 2, no changes in collaborative arrangements. There have been several minor changes in Senior Personnel. We report on these changes for the sake of completeness in reporting. Changes in senior personnel: There have been a few changes in project personnel, in particular owing to faculty departures. The most recent has been the retirement of Qin Zhang (WSU). His role has been taken over by Manoj Karkee and Lav Khot and there are no significant changes to salary or budget to report What opportunities for training and professional development has the project provided?The AgAID Institute contributed to the training and professional development of a variety of individuals. A summary of the numbers by the different categories is presented below. Please note that the reported numbers represent a lower bound on the number of trainees. For names and areas of the individuals involved please refer to the detailed annual review report submitted to the cognizant NIFA National Program Leader. 7 postdoctoral scholars 85 graduate (PhD or MS) students 25 resident undergraduate students 18 summer undergraduate research interns How have the results been disseminated to communities of interest?AgAID Institute's research hasled to 29 peer-reviewed papers in Y3, and a cumulative count of55 peer-reviewed publications in the first three years, and several more papers which are currently undergoing review. These publications have appeared in leading AI and Ag conference and journal venues. A complete list of publications along with their full citation information is provided in the Products section. The Institute's work has also led to numerous educational and curricular materials that targeted various levels of learners, at K-12, undergraduate, graduate, and post-doctoral researchers. The Institute members also organized various events such as workshops, tutorials, and panels at international conference venues aimed at the broader research community. A complete list of these outreach events and educational/curricular materials is provided in the Other Products section. Various members of the Institute also presented AgAID related materials at several meetings, including regional, national and international conferences. These presentations are listed below: Presentations in Y3: Streamflow Prediction with Uncertainty Quantification for Water Management:?A Constrained Reasoning and Learning Approach IJCAI 24 Jeju Island, South Korea Station-specific weather and inversion forecast model development and verification for abiotic stress management in fruit crops ASABE 2024 Annual International Meeting Anaheim, CA Sensor-fusion based sweet cherry (cv. Chelan) bud tissue temperature prediction model for effective spring frost management ASABE 2024 Annual International Meeting Anaheim, CA Machine Learning Improves Satellite-Based Evapotranspiration in a Semi-Arid Advective Environment ASABE AIM 2024 American Society of Agricultural and Biological Engineers Anaheim, California Smart wireless sensing network for frost management in sweet cherries CPAAS and Ag Weather Network Open House IAREC, Prosser, WA An overview of agri-food robotics at Oregon State University Dutch delegation: Orchard of the Future tour Yakima, WA Students on nonscientists: Ingroup identification, intergroup threat and agreement with the knowledge deficit hypothesis among STEM students in the US International Communication Association Annual Conference Gold Coast, Australia Dronesonde and Intelligent Sensing Network for Frost Management Research and Extension for Unmanned Aircraft Systems (UAS) Applications in U.S. Agriculture and Natural, Multistate Research Project Meeting Montana State University, Bozeman, MT Dynamically Refined 3D Modeling of Planar-Canopy Sweet Cherry Trees for Automated Pruning Research Field Trip MESA AgAID Prosser, WA Dynamically Refined 3D Modeling of Planar-Canopy Sweet Cherry Trees for Automated Pruning Research Field Trip MESA AgAID Prosser, WA Drones in Ag! FFA Convention FFA Pullman Dynamically Refined 3D Modeling of Planar-Canopy Sweet Cherry Trees for Automated Pruning Washington FFA Association Convention and Expo Future Farmers of America (FFA) Pullman, WA Drought in the West 2024 Western Interstate Region Conference Yosemite, California Irrigation and heat stress management in apple orchards Field day Roza, Prosser, WA Application of drones in agriculture Salmon Summit West, Science Field Trip for 4th graders Prosser, WA Uncovering implementable dormant pruning decisions from three different stakeholder perspectives NW Robotics Symposium Oregon State University AgAID Institute Overview Ag Threats Symposium WSDA Spokane, WA Gender-Inclusive Software and Beyond Sonoma State University Agri-food robotics research at OSU Oregon Dairy Industries (ODI) Annual Conference ODI Salem, OR Gender-Inclusive Software and Beyond University of South Florida Intelligent wireless sensing network for effective frost management in sweet cherry (cv. Chelan) orchards Honouring Undergraduate and Graduate Scholars Symposium Heritage University Toppenish, WA Drone applications in precision agriculture WSU Gear-Up Tour WSU Irrigated Agriculture Research and Extension Center (IAREC). Keynote address ACM Conference on Intelligent User Interfaces ACM Greensboro, South Carolina Early planting as an adaptation strategy to climate change: dafe-offs associated with reductions in heat-stress exposure 2024 WE Local Conference Society of Women Engineers Las Vegas, Nevada Attention-based Models for Snow-Water Equivalent Prediction IAAI-24 as part of AAAI 24 Vancouver, Canada Digital Technologies in Washington Vineyards Science in our Valley Wenatchee, WA Uncover how cutting-edge tech like AI, drones, and IoT is transforming vineyard management into a high-tech operation Science In Our Valley NCW Tech Alliance and Apple STEM Network Wenatchee Valley College's McGuire Event Center AI-driven Multi-Objective Design Optimization Bridge Program on AI for Design Problems, AAAI Conference, 2024 Vancouver, Canada Recent Advances in Robust Time-Series ML: From Theory to Practice Tutorial AAAI Conference Vancouver, Canada Artificial Intelligence in Agriculture 67th Annual IFTA Conference and Tours: Bridging the Gap Between Information and Action International Fruit Tree Association Yakima, WA AgAID: Making AI Work for Farm, Labor, and Water Intelligence QUAD meeting: Advancing Innovations for Empowering NextGen AGriculturE (AI-ENGAGE) NSF Furama Hotel, Singapore Improving Mechanical Shakers for Nut Crops Using an Advanced Data-Driven Model World Ag Expo 2024 World Ag Expo Tulare, California Precision Application Technologies Using Drones Teacher Drone Professional Development First Nations MESA Program Heritage University, Toppenish, WA AgAID Demo Farm CRESCENT Tour Yakima Valley College Prosser, WA Interactive experience for children ages 8-12 on electronics Field Day Prosser, WA AgAID Institute Overview and AI in Agriculture Washington Friends for Farms and Forests Annual Meeting Washington Friends for Farms and Forests Olympia, WA Climate, soils and landscape: Applying machine learning and principles of vinecology to sustain current and future winegrowing along the Pacific Coast of the Americas AGU 2023 Moscone Center, 747 Howard St, San Francisco, CA 94103 Evaluating a hydrology model's ability to simulate snow processes and identifying avenues for improvement American Geophysical Union San Francisco, California AgAID Institute Overview and Updates Washington State Tree Fruit Association 2023 Annual Meeting & NW Hort Expo Washington State Tree Fruit Association Kennewick, WA Dynamically Refined 3D Modelling of Planar-Canopy Sweet Cherry Trees for Automated Pruning WSTFA 2023 Research News Flash WSTFA / NW Hort Show Kannewick, WA Soil Mapping Technology for Perennial Crops II International Symposium on Precision Management of Orchards and Vineyards ISHS Australia An overview of the AgAID Institute WTFRC Technology Research Review Washington Tree Fruit Research Commission Virtual Lessons on Developing a Sensor Network in Grapes 2023 WSGS Annual Meeting and Trade Show Washington State Grape Society Church of the Nazarene 500 N. Elm, Grandview, WA Dynamically Refined 3D Modeling of Planar-Canopy Sweet Cherry Trees for Automated Pruning Boys and Girls Club tour IAREC Prosser, WA Drone Applications in Agriculture - AgAID use cases MESA Teacher Workshop on Drones Heritage University and YVTC First Nations MESA Program Tri-cities, WA Strategic Science Communication of Artificial Intelligence SAIL 2023 - Summit for AI Institutes Leadership NSF AI Institutes Atlanta, GA FFA Leadership Tour Filed Day Prosser, WA AgAID Institute Overview WSU Department of Horticulture Weekly Seminars Matthew Whiting Pullman, WA Enhancing Mechanical Harvesting Machines for Nut Trees Using a Data-Driven Model FIRA 2023 Ag Robotics Forum Salinas, California What do you plan to do during the next reporting period to accomplish the goals?Project F1: Cold hardiness prediction for frost mitigation (Grape, Sweet cherry) Model Deployment: Finalize our forecasting and uncertainty model and deploy on AgWeatherNet before the 2024-2025 dormancy period. Interface Use by Farmers and sientists Explore New Hybrid Mode Project F2: Site specific weather data imputation, forecasting and temperature inversion prediction Extend our model to handle larger datasets by working with NASCE and AgWeatherNet to develop a model that operates over many stations in a weather network (compared to just one station). Provide operationalization support and a roadmap with detailed requirements for deployment and experimentation Extend the model to support the concept of virtual weather stations Project F3: Weather and crop physiology data enabled AI models for automated heatstress mitigation (Apple, Grape) Investigation into science-driven robust models for apple fruit heat stress prediction. Real-time data fusion model validation to predict grape berry temperature. Project F4: Prediction of soil water content for deficit irrigation Tool for training soil-moisture content models. Construction of a physical testbed with experimental results evaluating the learning and control algorithms. Project F5: Building phenological tracking models and topological tools for multi-cultivar datasets for grapes (AI-driven) Publish the model running in real-time on a website. The next major work is in incorporating prediction intervals for our predictions. Predicting dormancy depth ?Project F6: Transfer learning for temporal process prediction New algorithms and paper on multi-source active transfer with application to cold hardiness. Collection of cold-hardiness data from farms based on guidance from active transfer algorithms. Project F7: AI-enabled farm decision support tools Extending the simulator with additional features for modeling richer crop, field, and weather characteristics. New algorithms and models for constraint learning. New algorithms for multi-task policy comparison Project F8: Robust model evaluation for geospatial problems Application: We will collaborate with other AgAID personnel to evaluate the cross-validation methods and recommend model evaluation strategies to best serve project goals. Development: Many problems are not purely spatial; instead, they have both spatial and temporal components. Project L1: Human-robot collaborative tools and approaches for dormant fruit treepruning New robot algorithms and control interfaces for pruning, leading to a new prototype end-effector that supports both ground-truth measurements (location and radii) and robust pruning. Image datasets with ground truth (both synthetic and real) User study identifying the most effective pruning training methods Field evaluation of the Mobile VS. Precision and recall metrics will be used to assess the quality and quantity of the Mobile VS predictions, respectively. A new pipeline to automate dataset relabeling using the skeletonized trees The Tree Pruning Robot (TPR), an integrated system using the Mobile VS, the UR5e robotic manipulator, a Clearpath Robotics' Warthog unmanned ground vehicle and a pruning unit, will be evaluated using similar performance parameters. Performance results from field trials of the prototype robot. A cycle time breakdown study will also be conducted to examine the various components contributing to the total cycle time required to generate cutting point estimations for a trellis section. Project L2: Human-robot collaborative tools and approaches for fruit tree flower/blossom thinning and fruitlet thinning Understanding human thinning decision making, developing thinning rules (from formative studies). Revised prototype, testing, crop yield, and quality analysis. Improved deep learning models for individual flower detection Project L3: Human-robot collaborative tools and approaches for fruit harvesting A larger, more extensive dataset of real apple picks from commercial orchards A tactile controller that uses pressure differentials to servo the gripper to the target fruit Project L4: All-terrain payload transport Extension of the system to support full carrier configuration control Extension to rough terrain that is reflective of Ag use cases. Extension to carriers and payload that are reflective of Ag use cases. Extension to integrate controller with terrain sensing. Project W1: Agricultural Digital Similars (AgSimilar) Improvements to the Washington agricultural digital similar based on our experimental case study Project W2: Value-based resource matching with fairness criteria: Application to Agricultural water trading An extension of this work with additional theoretical and experimental results will be submitted to a journal. Project W3: Canal/Waterway extraction and segmentation Extension of the current framework to the more capture more complex constraint i.e. flow constraints, directions of the flow Project W4: Machine learning models for streamflow forecasting Extension of the current streamflow prediction model to the more complex context of streamflow in human influenced watersheds. Developing conformal prediction methods for multi-target regression with provable marginal coverage guarantees motivated by the streamflow forecasting task where we need a forecast for some horizon (months or weeks or days). Developing novel sequential decision-making methods using offline datasets from past water decisions and apply them in collaboration with USBR. Project W5: A unifying information-theoretic perspective on evaluating generative Models Publication of a research paper summarizing findings and methodologies. Project W6: Attention-based transformer models for predicting snow water equivalent New AI strategies and approaches will be developed to predict for historically unseen locations. We will generate a spatially-complete country-scale SWE map for the entire U.S. We will initiate collaborations with USBR and with the USDA National Resources Conservation Service (NRCS) for enabling this data service, so that a broad global-scale access to our data set becomes possible. On the AI side, several other venues for exploration are also planned including (but not limited to): i) evaluating the value of modeling the problem as spatiotemporal graphs; ii) characterizing the role of different variables, and iii) coupling with process-based models to ensure scientific consistency and model interpretability. Project W7: Applications of machine learning frameworks for explaining complex geospatialsimulations Publication of our research Project W8: IrrNet: Advancing irrigation mapping with incremental patch size training onremote sensing imagery ? To generalize our model for different agricultural assets Publication of a research paper summarizing our further findings and methodologies Exploring other models, integrating multimodal data to improve the overall performance and interpretability of the model Education Continue to train graduate and undergraduate students, and mentor postdoctoral scholars for research Conduct AgAID summer undergraduate research internships Recruit students into PhD and MS degree programs in AI and in digital agriculture related topics Expand and conduct MESA field trips and refine curriculum based on survey results Expand curricular opportunities in collaboration with Agricultural Educators and/or FFA. Extension and workforce development Continue conducting learning circles for various research thrusts and to include new stakeholder interactions Continue extension activities for workforce training and broadening participation Develop strategy for Early Adopters Network Continue field days and webinar series Broadening participation Continue bilingual training (Spanish Language) and outreach Pilot AgAID training/curriculum materials into HOEEP program to train current workforce
Impacts
What was accomplished under these goals?
A selective list of top accomplishments in Year 3 under different categories: Ag-inspired AI research Development, evaluation, extension and deployment of cold hardiness predictive models for frost mitigation in grapes and sweet cherry (farm intelligence) Development and testing of tools for site-specific weather data imputation, forecasting and temperature inversion prediction (farm intelligence) Development of a new specialty crop simulator and related benchmarks (farm intelligence) Development and evaluation of human-robot collaborative tools and approaches for dormant fruit tree pruning with applications to apples and sweet cherry pruning (labor intelligence) Development and evaluation of human-robot collaborative tools and approaches for fruit tree flower/blossom thinning and fruitlet thinning (labor intelligence) Development and evaluation of human-robot collaborative tools and approaches for fruit harvesting (labor intelligence) Design of new spatio-temporal and information-theoretic models for predicting streamflow, snow-water equivalent, and irrigation planning (water intelligence) Conceptualization and design of a digital twin for agricultural lands (AgSimilars) to facilitate regional season-scale agricultural planning (water intelligence) Foundational AI research Advances in multi-task learning, transfer learning, and deep reinforcement learning New algorithms in representation learning, science-guided ML, and attention mechanisms for spatio-temporal forecasting and prediction tasks Improvement of uncertainty quantification of deep classifiers Development of foundations for data imputation models Deep Learning Models for Instance Segmentation (to generate orchard-scale tree simulators) Simulation-to-real learning of hybrid vision/interaction controllers for robot manipulation Design of gender & socioeconomic-inclusive human-AI workflows Cross-thrust integration Deployment of sensing instruments for research and training at three Demo farm sites, involving tree fruit orchards and grape vineyards Continued expansion of data and modeling workflows and evaluation of computational platforms for research use Continued expansion and use of online resources and collaborative tools for intra-team training and collaborations Education Interdisciplinary training of Master and PhD students, and postdoctoral mentoring in AI and Digital Ag Development of K-12 hands-on, field-based curricular materials for middle schoolers and high schoolers Summer undergraduate internships, with inter-generational mentors, for 47 students (to date) Drone workshop for high school agricultural science teachers at their annual conference, and for >130 FFA students at their annual conference, in Year 3.. Development of Ag Innovations CDE with the partnership of Future Farmers of America, to be piloted in Year 4 Extension and workforce development Learning circles and formative studies with Ag user groups, policy makers, farm workers and managers, and Hispanic community Preparation of materials for workforce training in orchard management Field days in orchard management (including in Spanish) Broadening participation and diversity Various K-12 training and outreach activities at UC Merced (for Hispanic/Latinx and rural Californians) including coding camps and robotics programs, and at the International FIRA Robotics Conference Four field trips in Year 3 for K-12 MESA (Math Engineering Science Achievement) Hispanic/Latine/Native middle and high schoolers Recruitment and training of diverse groups as part of graduate and undergraduate research training Multi-organizational synergies/achievements Engagement with Hitech and AgTech industry Outreach and presentations at various partner events including (but not limited to) AI and robotic conferences, and horticultural/geological society meetings Communication and securing infrastructure support from commissions Expansion of research into other specialty crops (berries, potatoes) Knowledge transfer Published or submitted at least 43 papers (in Year 3) at refereed publication venues Evaluation of tool dissemination portals in farm management, labor management, and water resources management Impact of the institute as a nexus point for collaborative efforts Coordination and collaboration with sister NIFA AI Institutes (AIFARMS, AIFS, AIIRA, AI-CLIMATE) as well as a Memorandum of Understanding with NSF AI institutes (ICICLE) Continue international collaborations (with Australia, Chile, and Netherlands) as part of the NSF-NIFA AI Institutes International Collaboration Supplements program including student visits and training Explore partnerships with PNW (Washington and Oregon states) Ag industry and tech industry Conduct an Indo-US collaboration initiation workshop on digital agriculture Co-organize the Ag-AI Visioning Conference in Washington DC Outreach through presentations and demos at NSF AI Hill day, White House OSTP AI Aspirations conference, NSF QUAD AI-Engage summit, and FIRA conference Engage with local WA state Ag industry through Ag Tech commercialization workshops, field days, and NW Hort Show On-going projects with specific accomplishments highlighted in the long report: Project F1: Cold hardiness prediction for frost mitigation (Grape, Sweet cherry) Project F2: Site specific weather data imputation, forecasting and temperature inversion prediction Project F3: Weather and crop physiology data enabled AI models for automated heat stress mitigation (Apple, Grape) Project F4: Prediction of soil water content for deficit irrigation Project F5: Building phenological tracking models and topological tools for multi-cultivar data sets for grapes (AI-driven) Project F6: Transfer learning for temporal process prediction Project F7: AI-enabled farm decision support tools Project F8: Robust model evaluation for geospatial problems Project L1: Human-robot collaborative tools and approaches for dormant fruit tree pruning Project L2: Human-robot collaborative tools and approaches for fruit tree flower/blossom thinning and fruitlet thinning Project L3: Human-robot collaborative tools and approaches for fruit harvesting Project L4: All-terrain payload transport Project W1: Agricultural Digital Similars (AgSimilar) Project W2: Value-based resource matching with fairness criteria: Application to agricultural water trading Project W3: Canal/Waterway extraction and segmentation Project W4: Machine learning models for streamflow forecasting Project W5: A unifying information-theoretic perspective on evaluating generative models Project W6: Attention-based transformer models for predicting snow water equivalent Project W7: Applications of machine learning frameworks for explaining complex geospatial simulations Project W8: IrrNet: Advancing irrigation mapping with incremental patch size training on remote sensing imagery Project D1: Demo farm at WSU Project D2: Demo farm at WVC and commercial orchard in Wenatchee WA Project HAI1: Design of gender- and socioeconomic-inclusive human-AI workflows
Publications
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Hoque, Oishee Bintey, Samarth Swarup, Abhijin Adiga, Sayjro Kossi Nouwakpo, and Madhav Marathe. IrrNet: Advancing Irrigation Mapping with Incremental Patch Size Training on Remote Sensing Imagery. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. pp. 5460-5469
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Thapa, Krishu, Bhupinderjeet Singh, Supriya Savalkar, Alan Fern, Kirti Rajagopalan, and Ananth Kalyanaraman. Attention-based Models for Snow-Water Equivalent Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 38(21), 22969-22975. https://doi.org/10.1609/aaai.v38i21.30337
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Sapkota, Ranjan, Dawood Ahmed, and Manoj Karkee. Comparing YOLOv8 and Mask R-CNN for instance segmentation in complex orchard environments. Artificial Intelligence in Agriculture. vol. 13, pp. 84-99. ISSN 2589-7217.
https://doi.org/10.1016/j.aiia.2024.07.001
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Zhao, Anni, Arash Toudeshki, Reza Ehsani, Joshua H. Viers, and Jian-Qiao Sun. "Evaluation of Neural Network Effectiveness on Sliding Mode Control of Delta Robot for Trajectory Tracking." Algorithms. vol. 17, no. 3, article 113. https://doi.org/10.3390/a17030113
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Farajijalal, Mohsen, Samira Malek, Arash Toudeshki, Joshua H. Viers, and Reza Ehsani. Data-Driven Model to Improve Mechanical Harvesters for Nut Trees. American Society of Agricultural and Biological Engineers, 2024 ASABE Annual International Meeting. doi:10.13031/aim.202400858
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Sapkota, Ranjan, Dawood Ahmed, Martin Churuvija, and Manoj Karkee. "Immature Green Apple Detection and Sizing in Commercial Orchards Using YOLOv8 and Shape Fitting Techniques." In IEEE Access, vol. 12, pp. 43436-43452, 2024, doi: 10.1109/ACCESS.2024.3378261
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Marshall, Adrienne, John Abatzoglou, Dennis Lettenmaier, Stefan Rahimi, and Alex Hall. Californias 2023 snow deluge: Contextualizing an extreme snow year against future climate change. Proceedings of the National Academy of Sciences. vol. 121, no. 20. doi: 10.1073/pnas.2320600121
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Blanco, Victor, Lee Kalcsits. Relating microtensiometer-based trunk water potential with sap flow, canopy temperature, and trunk and fruit diameter variations for irrigated Honeycrisp apple. Frontiers in Plant Science. vol. 15. doi: 10.3389/fpls.2024.1393028. ISSN 1664-462X
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Kiraga, Shafik, R. Troy Peters, Behnaz Molaei, Steven R. Evett, and Gary Marek. "Reference Evapotranspiration Estimation Using Genetic Algorithm-Optimized Machine Learning Models and Standardized PenmanMonteith Equation in a Highly Advective Environment." Water. vol 16, no. 1: 12.
https://doi.org/10.3390/w16010012
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Adiga, Abhijin, Yohai Trabelsi, Tanvir Ferdousi, Madhav Marathe, S. S. Ravi, Samarth Swarup, Anil Kumar Vullikanti, Mandy L. Wilson, Sarit Kraus, Reetwika Basu, Supriya Savalkar, Matthew Yourek, Michael Brady, Kirti Rajagopalan, and Jonathan Yoder. Value-based Resource Matching with Fairness Criteria: Application to Agricultural Water Trading. In Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS '24). pp. 1321. doi: 10.5555/3635637.3662847
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Garcia, Rosalinda, Patricia Morreale, Gail Verdi, Heather Garcia, Geraldine Jimena Noa, Spencer P. Madsen, Maria Jesus Alzugaray-Orellana, Elizabeth Li, and Margaret Burnett. The Matchmaker Inclusive Design Curriculum: A Faculty-Enabling Curriculum to Teach Inclusive Design Throughout Undergraduate CS. In Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI '24). Article 657, pp. 122. https://doi.org/10.1145/3613904.3642475
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Das, Shubhomoy, Md Rakibul Islam, Nitthilan Kannappan Jayakodi, and Janardhan Rao Doppa. "Effectiveness of Tree-based Ensembles for Anomaly Discovery: Insights, Batch and Streaming Active Learning." Journal of Artificial Intelligence Research. vol. 80, pp. 127-170. https://doi.org/10.1613/jair.1.14741
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Chemingui, Yassine, Aryan Deshwal, Trong Nghia Hoang, and Janardhan Rao Doppa. "Offline model-based optimization via policy-guided gradient search." In Proceedings of the AAAI Conference on Artificial Intelligence. vol. 38, no. 10, pp. 11230-11239. https://doi.org/10.1609/aaai.v38i10.29001
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Fern, Alan, Margaret Burnett, Joseph Davidson, Janardhan Rao Doppa, Paola Pesantez-Cabrera, and Ananth Kalyanaraman. AgAID InstituteAI for Agricultural Labor and Decision Support. AI Magazine 45: 99104.
https://doi.org/10.1002/aaai.12156
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Savalkar, Supriya, Md. Redwan Ahmad Khan, Bhupinderjeet Singh, Matt Pruett, R. Troy Peters, Claudio O St�ckle, Sean E. Hill, and Kirti Rajagopalan. Errors in temporal disaggregation of temperature can lead to non-negligible biases in agroecosystem risk assessment. Agricultural and Forest Meteorology. vol 349. ISSN 0168-1923. https://doi.org/10.1016/j.agrformet.2024.109952
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Bhattarai, Uddhav, Qin Zhang, Manoj Karkee. Design, integration, and field evaluation of a robotic blossom thinning system for tree fruit crops. Journal of Field Robotics, 41, 13661385. https://doi.org/10.1002/rob.22330
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Zhao, Anni, Arash Toudeshki, Reza Ehsani, Joshua H. Viers, and Jian-Qiao Sun. "Robustness improvement of optimal control in terms of RBFNN with empirical model reduction and transfer learning." International Journal of Control. pp. 1-15
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Kirkpatrick, Alex, Amanda Boyd, and Jay Hmielowski. Who shares about AI? Media exposure, psychological proximity, performance expectancy, and information sharing about artificial intelligence online. AI & Society.
https://doi.org/10.1007/s00146-024-01997-x
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Ahmed, Dawood, Ranjan Sapkota, Martin Churuvija, Matthew Whiting, and Manoj Karkee. Slicing-Aided Hyper Inference for Enhanced Fruit Bud Detection and Counting in Apple Orchards during Dormant Season. American Society of Agricultural and Biological Engineers, 2024 ASABE Annual International Meeting. doi:10.13031/aim.202401055
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Sapkota, Ranjan, Dawood Ahmed, Martin Churuvija, Syed Usama Bin Sabir, Safal Kshetri, and Manoj Karkee. Human-Assisted Robotic Trials to Nature-Assisted Strategies for feasibility of Automated Fruitlet Thinning in Commercial Orchards. American Society of Agricultural and Biological Engineers, 2024 ASABE Annual International Meeting. doi:10.13031/aim.202400074
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Gharsallaoui, Mohammed Amine, Bhupinderjeet Singh, Supriya Savalkar, Aryan Deshwal, Ananth Kalyanaraman, Kirti Rajagopalan and Janardhan Rao Doppa. Streamflow Prediction with Uncertainty Quantification for Water Management: A Constrained Reasoning and Learning Approach. Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. pp. 7269--7277.
https://doi.org/10.24963/ijcai.2024/804
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Chatterjee, Amreeta, Rudrajit Choudhuri, Mrinmoy Sarkar, Soumiki Chattopadhyay, Dylan Liu, Samarendra Hedaoo, Margaret Burnett, and Anita Sarma. Debugging for Inclusivity in Online CS Courseware: Does it Work? In Proceedings of the 2024 ACM Conference on International Computing Education Research. vol. 1, pp. 419433. https://doi.org/10.1145/3632620.3671117
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Garcia, Rosalinda, Patricia Morreale, Pankati Patel, Jimena Noa Guevara, Dahana Moz-Ruiz, Sabyatha Satish Kumar, Prisha Velhal, Alec Busteed, and Margaret Burnett. Beyond Awareness : If We Teach Inclusive Design, Will Students Act On It?. In Proceedings of the 2024 ACM Conference on International Computing Education Research. vol. 1, pp.434451.
https://doi.org/10.1145/3632620.3671101
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Moyers, Kelley, John T. Abatzoglou, Alvar Escriva-Bou, Josu� Medell�n-Azuara, and Joshua H. Viers. An invisible water surcharge: Climate warming increases crop water demand in the San Joaquin Valleys groundwater-dependent irrigated agriculture. PLOS Water. vol. 3, no.(3): e0000184.
https://doi.org/10.1371/journal.pwat.0000184
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Gorthi, Srikanth, Gwen Hoheisel, and Lav Khot. Is it important to monitor bud tissue temperature for spring frost management in sweet cherry? WSU Tree Fruit, Fruit Matters
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Amogi, Basavara, and Sean Hill. Temperature Inversion Forecasts Available for AgWeatherNet Mesonet Tower Stations. WSU Tree Fruit, Fruit Matters
- Type:
Other
Status:
Published
Year Published:
2024
Citation:
Schrader, Jake, and Lav Khot. Smart Vineyard Concepts to Reality in Washington State. WSU Viticulture and Enology, Extension
- Type:
Journal Articles
Status:
Accepted
Year Published:
2024
Citation:
Anderson, Andrew, Jimena Noa Guevara, Fatima Moussaoui, Tianyi Li, Mihaela Vorvoreanu, and Margaret Burnett. Measuring User Experience Inclusivity in Human-AI Interaction via Five User Problem-Solving Styles. ACM Transactions on Interactive Intelligent Systems. https://doi.org/10.1145/3663740
- Type:
Journal Articles
Status:
Accepted
Year Published:
2024
Citation:
Amogi, Basavaraj R., Nisit Pukrongta, Lav R. Khot, Bernardita V. Sallato. Edge compute algorithm enabled localized crop physiology sensing system for apple (Malus domestica Borkh.) crop water stress monitoring. Computers and Electronics in Agriculture. vol. 224. ISSN 0168-1699.
https://doi.org/10.1016/j.compag.2024.109137
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2025
Citation:
Islam, Mohammad Rafid Ul, Prasad Tadepalli, Alan Fern. Self-attention-based Diffusion Model for Time-series Imputation in Partial Blackout Scenarios. Refereed Proceeding AAAI Conference on Artificial Intelligence
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2025
Citation:
Pandit, Bikram, Ashutosh Gupta, Mohitvishnu S. Gadde, Addison Johnson, Aayam Kumar Shrestha, Helei Duan, Jeremy Dao, Alan Fern. Learning Decentralized Multi-Biped Control for Payload Transport. Refereed Proceeding Conference on Robot Learning
- Type:
Journal Articles
Status:
Under Review
Year Published:
2025
Citation:
Singh, Bhupinderjeet, Tanvir Ferdousi, John Abatzoglou, Samarth Swarup, Jennifer adam, and Kirti Rajagopalan. Sensitivity of Snow Magnitude and Duration to Hydrology Model Parameters. Journal of Hydrology.
http://dx.doi.org/10.2139/ssrn.4795311
- Type:
Journal Articles
Status:
Under Review
Year Published:
2025
Citation:
Flynn, Deanna, Abhinav Jain, Heather Knight, Cristina G. Wilson, Cindy Grimm. Uncovering implementable dormant pruning decisions from three different stakeholder perspectives. Journal of Cognitive Engineering and Decision Making. https://arxiv.org/abs/2405.04030
- Type:
Journal Articles
Status:
Under Review
Year Published:
2025
Citation:
Churuvija, Martin, Ranjan Sapkota, Dawood Ahmed, Manoj Karkee. Dynamically Refined 3D Modeling of Planar-Canopy Sweet Cherry Trees for Automated Pruning. Computers and Electronics in Agriculture
- Type:
Journal Articles
Status:
Under Review
Year Published:
2025
Citation:
Brown, Jostan, Achyut Paudel, Deven Biehler, Ashley Thompson, Manoj Karkee, Cindy Grimm, and Joseph Davidson. Tree detection and in-row localization for autonomous precision orchard management. Computers and Electronics in Agriculture
- Type:
Journal Articles
Status:
Under Review
Year Published:
2025
Citation:
Abatzoglou, John, Joshua Viera, Josue Medellin, Kirti Rajagopan, Emily Williams, Alvar Escriva, and Justin Huntington. Shorter Growing Seasons May Moderate Climate Change Effects on Crop Water Demand. Environmental Research Letters
- Type:
Journal Articles
Status:
Under Review
Year Published:
2025
Citation:
Saxena, Aseem, Paola Pesantez-Cabrera, Jonathan Magby, Markus Keller, Alan Fern. Multi-Task Learning for Temporal Processes: A Case Study on Modeling Plant Cold Hardiness. Springer Machine Learning
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2025
Citation:
You, Alex, Jochen Hemming, Cindy Grimm, and Joseph Davidson. A real-time, hardware agnostic framework for close-up branch reconstruction using RGB data. 2024 IEEE International Conference on Robotics and Automation (ICRA)
- Type:
Journal Articles
Status:
Under Review
Year Published:
2025
Citation:
Supriya Savalkar, Michael Pumphrey, Kimberly Campbell, Fabio Scarpare, Tanvir Ferdousi, Samarth Swarup, Claudio Stockle, Kirti Rajagopalan. Earlier planting in a future climate fails to replicate historical production conditions for US spring wheat. Nature Food Journal.
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2024
Citation:
Gorthi, Srikanth, Dattatray Bhalekar, Lav Khot, and Markus Keller. Modeling grape berry temperature for effective heat stress management in vineyards. In 2024 IEEE International Workshop on Metrology for Agriculture and Forestry (MetroAgriFor)
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2024
Citation:
Amogi, Basavaraj, Lav Khot, and Bernardita Sallato. Localized Crop Physiology Sensing System Driven Apple Fruit Color Progression Monitoring. In 2024 IEEE International Workshop on Metrology for Agriculture and Forestry (MetroAgriFor)
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2024
Citation:
Goebel, Kristen, Paola Pesantez-Cabrera, Markus Keller, and Alan Fern. Transfer Learning via Auxiliary Labels for Cold-Hardiness Prediction. IEEE Conference on Machine Learning and Applications
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2024
Citation:
Kokten, Ozmen E., Raviv Raich, James Holmes, and Alan Fern. Learning Extended Forecasts of Soil Water Content via Physically-Inspired Autoregressive Models. IEEE Conference on Machine Learning and Applications
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2025
Citation:
Ugwu, Chibuike Emmanuel, Yan Yan, Diane Cook, and Jana Doppa. Adaptive Prediction Regions for Multi-Target Regression. AAAI-2025 Conference
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2025
Citation:
Shahrokhi, Hooman, Devjeet Raj Roy, Yan Yan, Venera Arnaoudova, and Jana Doppa. Adaptive Prediction Sets for Generative Models. AAAI-2025 Conference
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2025
Citation:
Chemingui, Yassine, Aryan Deshwal, Honghao Wei, Alan Fern, and Jana Doppa. Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning. AAAI-2025 Conference
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2024
Citation:
Belakaria, Syrine, Benjamin Letham, Jana Doppa, Barbara E Engelhardt, Stefano Ermon, and Eytan Bakshy. Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes. NeurIPS-2024 Conference
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2024
Citation:
Shi, Yuanjie, Subhankar Ghosh, Taha Belkhouja, Janardhan Rao Doppa, and Yan Yan. Conformal Prediction for Class-wise Coverage via Augmented Label Rank Calibration. NeurIPS-2024 Conference
- Type:
Journal Articles
Status:
Under Review
Year Published:
2025
Citation:
Singh, Bhupinderjeet, Mingliang Liu, John Abatzoglou, Jennifer Adam, Kirti Rajagopalan. Dynamic precipitation phase partitioning improves modeled simulations of snow across the Northwest US. Hydrology and Earth System Sciences Journal
- Type:
Journal Articles
Status:
Under Review
Year Published:
2025
Citation:
Koul, Anurag, Mariano Phielipp, and Alan Fern. Offline Policy Comparison with Confidence: Benchmarks and Baselines. Transactions on Machine Learning Research. https://openreview.net/revisions?id=hfE9u5d3_dw
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2025
Citation:
Shahrokhi, Hooman, Yuanjie Shi, Subhanrak Ghosh, Jana Doppa, and Yan Yan. Direct Prediction Set Minimization via Conformal Training of Deep Classifiers. AAAI-2025 Conference
|
Progress 09/01/22 to 08/31/23
Outputs
Target Audience: Students (K-12, associate degree programs, undergraduate, graduate) Postdoctoral researchers Faculty at all AgAID member organizations External research collaborators in academia and industry Specialty crop growers Specialty crop agricultural farm managers and workers Crop commissions and crop consultants Water irrigation districts State departments of agriculture and ecology K-12 educators Associate degree program and undergraduate program educators IT industry partners AgTech and FarmTech industry partners Federal funding agencies including USDA NIFA and NSF Population groups: Underrepresented minority groups including (but not limited to) Hispanic/Latinx and Native American First generation college students Underrepresented genders Changes/Problems:There has been no change in the scope or objectives of the project, and in Year 2, no changes in collaborative arrangements. There have been several minor changes in Senior Personnel. We report on these changes for the sake of completeness in reporting. Changes in senior personnel: There have been a few changes in project personnel, in particular owing to faculty departures. Senior Personnel Minsuk Kahng at OSU left academia for industry. His role in the original proposal was research on AI and HCI design, and his role and responsibilities have been taken on by existing members of the OSU team. We also have a new AI member Sandhya Saisubramanian from OSU who is now working with our farm intelligence team. Senior Personnel Jenny Bolivar Medina has departed WSU. Her original role was supporting our Extension efforts. Her role and responsibilities have been taken on by Gwen Hoheisel.? What opportunities for training and professional development has the project provided?The AgAID Institute contributed to the training and professional development of a variety of individuals. A summary of the numbers by the different categories is presented below. Please note that the reported numbers represent a lower bound on the number of trainees. For names and areas of the individuals involved please refer to the detailed annual review report submitted to the cognizant NIFA National Program Leader. 5 postdoctoral scholars 42 graduate (PhD or MS) students 7 resident undergraduate students 15 summer undergraduate research interns How have the results been disseminated to communities of interest?AgAID Institute's research has so far led to 26 peer-reviewed publications accepted or published in its first two years, and 6 more papers which are currently undergoing review. These publications have appeared in leading AI and Ag conference and journal venues. A complete list of publications along with their full citation information is provided in the Products section. The Institute's work has also led to numerous educational and curricular materials that targeted various levels of learners, at K-12, undergraduate, graduate, and post-doctoral researchers. The Institute members also organized various events such as workshops, tutorials, and panels at international conference venues aimed at the broader research community. A complete list of these outreach events and educational/curricular materials is provided in the Other Products section. Various members of the Institute also presented AgAID related materials at several meetings, including regional, national and international conferences. These presentations are listed below. Presentations: Innovations in Specialty Crop Harvest Technologies. Tri-Cities, Richland, WA. Sept. 2022. Keynote Address, JP Morgan/Chase Developers Conference, Plano, TX. Oct 2022. Robotic orchard pruning development, FIRA USA 2022, University of California and Western Growers, Fresno, California. Oct. 2022. Science and engineering of complex networks: The central role of AI and computing. WSU, Pullman WA. Oct. 2022. Where are the orchard bots? Thirty years of research on robotic fruit harvesting. OSU, Corvallis OR. Nov. 2022. A New Approach to Reducing Cold Damage in Fruit Crops with plant-based dispersions. WSU Tree Fruit Extension, WSU Tri-Cities, Richland, WA. Nov. 2022. Technology for Trade: New Tools and New Rules for Water Use and Allocation in Agriculture and Beyond. WSU Yakima County Extension. Nov. 2022. l cambio climático y sus efectos sobre la producción de frutas (Climate change effects on fruit production - Spanish). Washington State Tree Fruit Association Annual Meeting, Wenatchee, WA. Dec. 2022. Finding AI's Faults with AAR/AI: An Empirical Study. ACM International Conference on Intelligent User Interfaces, Sydney, Australia. March 2023. AgAID Ethics. AIVO. May 2023. Towards tactile orchard robotics. Corvallis, OR, May 2023. Mitigation Strategies for Heat Stress and Sunburn in Apples. Columbia Tree Fruit Club, Kennewick, WA. May 2023. Panel: "Entering a New Age: Community and Education Panel". WAAESD, Tri-Cities, WA. June 2023. Ag Educators Conference Workshop. Washington Association of Agricultural Educators, Spokane, WA. June 2023. Follow the leader: A path generator and controller for precision tree scanning with a robotic manipulator. 2023 European Conference on Precision Agriculture, University of Bologna, Italy. July 2023. Machine Vision System for Early-stage Apple Flowers and Flower Clusters Detection for Precision Thinning and Pollination. IFAC World Congress 2023, Yokohama, Japan. July 2023. Comparison of simulated and observed snow magnitude and phenology metrics. American Society of Agricultural and Biological Engineers. July 2023. The AgAID Institute - Conversaciones sobre AI en Español. AI Expo 2023, Wenatchee, WA. Aug. 2023. The AgID Institute - Precision Agriculture for Pruning, Thinning, and Harvesting. The Future of AI Forum - U.S. Senator Maria Cantwell, Seattle, WA. Aug. 2023. ? What do you plan to do during the next reporting period to accomplish the goals?Farm Intelligence Projects F1: Cold hardiness prediction for frost mitigation Develop approaches for transfer learning with only auxiliary target tasks Improve cold-hardiness model for forecasting and deploy on AgWeatherNet before the 2023 dormancy period. Explore approaches for uncertainty quantification F2: Weather data imputation and forecasting algorithms for site-specific modeling and use Show the modeled hourly offset estimates in graphical form and display the station correlation values on a map Experimentation of new models on missing data scenarios and correlation structures in time-series data. F3: Prediction of soil water content for deficit irrigation Model development work using Jim Holmes data to identify the best architecture and inputs. Explore the use of multi-task learning to develop site specific models that are optimized for specific field locations, but can leverage data from other field locations. Launch a new effort on decision support for deficit irrigation. F4: AI-enabled farm decision support tools Develop a new specialty-crop simulator for capturing qualitative aspects of specialty crops relevant to decision support New algorithms/models for OPCC and evaluation for safe decision support within the specialty crop simulator F5: Building a topological data analytical framework for multi-cultivar spatio-temporal data Investigate approaches that can use RNN model traces for mapping to crop phenological states. F6: Temperature Inversion Prediction Implement models of increasing complexity to incorporate spatial and temporal information from the sensors. Apply our models to weather data from WA state F7: Robust model evaluation for geospatial problems Evaluate cross-validation methods and recommend model evaluation strategies to best serve project goals. F8. Weather and crop physiology data enabled AI model for automated heat stress mitigation (Apple, Grape) Heat stress prediction models development, refinements, and testing in Demo Farm sites (apple and grapes), with pseudo-actuation triggers. Porting crop specific models in AgWeatherNet ecosystem and beta testing with few growers. Labor Intelligence Projects L1: Automated tree fruit pruning Develop a pruning training interface for orchard workers (in conjunction with our other team members, using the SocialMag facet-informed approach) to validate our findings from formative human studies. Improve the quality of digital tree models to help increase the robustness of cross-domain tree-branch semantic segmentation. Develop a 3D Follow the Leader controller that uses just a 2D camera feed to model the structure of the tree on the fly, estimate the orientation of branches, and keep the robot a set distance away from the canopy. Additional system integration, lab evaluations, and field evaluations of the pruning robot prototype. L2: Automated flower thinning Understanding human thinning decision making, developing thinning rules (from formative studies). Revised prototype, testing, crop yield, and quality analysis. Improved deep learning models for individual flower detection. Water Intelligence Projects W1: Agricultural Digital Twins (AgTwin) Expand our agricultural digital twin to identify a concrete application for the population to run as an experimental case study W2: Orchard age prediction Determine the best way to apply trellis classification to orchard age prediction, ultimately resulting in a model that can predict orchard age with less historical data than current methods require. W3: Canal/Waterway extraction and segmentation Train model over all 29 images, utilizing image-wise k-fold cross validation to evaluate the performance Explore methods to fill in gaps in segmentation outputs W4: Streamflow forecasting Extend our streamflow prediction model to incorporate more complex context including human influence Develop conformal prediction methods for spatio-temporal prediction tasks and proving marginal coverage guarantees W5: Fallow prediction Develop machine learning models for fallow prediction using over 20 years of remote sensing data. Expand analysis to include California and exploration of additional aspects such as field age estimation and changes in crop mixes. W6: A machine learning framework to explain complex geospatial simulations: A climate change case study Apply the method to evaluate the role of VIC inputs in explaining CropSyst outputs (e.g., crop yield). W7: Attention-based transformer models for predicting snow water equivalent Generate a spatially-complete country-scale SWE map for the entire U.S. Extend AI model to include non-trivial ensemble methods, alternate formulations involving graphs, characterize the role of different variables, andcouple with process-based models to ensure scientific consistency and model interpretability. Cross-cutting Research Projects D1: Demo Farm at WSU Use Demo farm sites for research thrust data collection and ground truthing, and for training including boot camps and undergraduate research experience Prototype AI models for automation of deficit irrigation in grapevine. Testing of grape cold hardiness model for automated actuation of mitigation measures. Develop robust wireless sensor network D2: Demo farm at WVC and commercial orchard in Wenatchee WA Install the Phytech monitoring and automation services at WVC's campus and train students Develop internship opportunities for students for precision agriculture technologies Train orchard workers, managers and supervisors. Human-AI workflows Empirical and longitudinal field studies of AI developers using GenderMag and/or SESMag on their own products. Lab study of end users, to evaluate the effectiveness of the inclusivity fixes produced by the above AI developers above. Validation of both SESMag surveys. Deploy use of the SESMag and GenderMag surveys in AgAID products, to enable measurement of these products' inclusivity. Education Continue to train graduate and undergraduate students, and mentor postdoctoral scholars for research Conduct AgAID summer undergraduate research internships Recruit students into PhD and MS degree programs in AI and in digital agriculture related topics Expand and conduct MESA field trips and refine curriculum based on survey results Expand curricular opportunities in collaboration with Agricultural Educators and/or FFA. Extension and workforce development Continue conducting learning circles for various research thrusts and to include new stakeholder interactions Continue extension activities for workforce training and broadening participation Develop strategy for Early Adopters Network Continue field days and webinar series (Orchards) Broadening participation Pilot AgAID training/curriculum materials into HOEEP program to train current workforce Mentor students under LSAMP program Continue bilingual training (Spanish Language) and outreach
Impacts
What was accomplished under these goals?
Ag-inspired AI research Development, evaluation and extension of cold hardiness predictive models for frost mitigation in grapes (impacts farmers using AI) Sensor deployment and preliminary development of AI-driven deficit irrigation models for grapes (impacts farmers using AI) Development of prescription, planning and control models for intelligent dormant pruning for apple (impacts farmers using AI) Design of deep learning models for automated blossom thinning for apple (impacts farmers using AI) Design of new spatio-temporal models for predicting hydrological variables (impacts irrigation district managers managing water allocation) Conceptualization of a digital twin for agricultural lands (AgTwins) (impacts regional and federal resource planners) Aggregation of historical data and preliminary models for soil water content in vineyards (impacts Ag researchers) Foundational AI research Advances in multi-task learning and deep reinforcement learning (impacts AI developers) New algorithms in representation learning and science-guided ML for spatio-temporal forecasting and prediction tasks (impacts AI developers) Improvement of uncertainty quantification of deep classifiers (impacts AI developers) Development of foundations for data imputation models (impacts AI developers) Simulation-to-real learning of hybrid vision/interaction controllers for robot manipulation (impacts AI developers) Development of foundations for socio-economic mag (impacts AI developers) Cross-thrust integration Deployment of sensing instruments at two Demo farm sites (impacts researchers and workforce training facilities) Continued expansion of data and modeling workflows (impacts AI researchers) Education Interdisciplinary training of graduate students and postdoctoral mentoring (impacts next generation training) Development of K-12 hands-on, field-based curricular materials (impacts next generation training) Summer undergraduate internships for 29 students, with inter-generational mentoring (impacts next generation training) First AgAID-sponsored Digital AgAthon in partnership with Microsoft (impacts next generation training) AI Expo aimed at educators at a STEM summit (impacts next generation training) Extension and workforce development Learning circles with Ag user groups, policy makers, and Hispanic community (impacts current Ag workforce and AI tool developers) Field days for workforce training in orchard management (impacts current Ag workforce) Broadening participation and diversity Various K-12 training and outreach activities at UC Merced (impacts next generation training) Two field trips for K-12 MESA Yakama Nation middle schoolers (impacts next generation training) Recruitment and training of diverse groups as part of graduate and undergraduate research training (impacts next generation training) Multi-organizational synergies Engagement with Hitech and AgTech industry (impacts academic-industry collaborations) Outreach and presentations at various partner events including AI/robotic conferences (impacts AI and Ag research communities) Expansion of research into other specialty crops (berries, potatoes) (impacts farmers) Knowledge transfer Published or submitted at least 32 papers at refereed publication venues (impacts AI and Ag research communities) Evaluation of tool dissemination portals in farm management (impacts farm managers) Impact of the institute as a nexus point for collaborative efforts Coordination with sister NIFA AI Institutes and with ICICLE (impacts AI and Ag researchers) Initiate international collaborations (impacts AI and Ag researchers) Explore partnerships with industry (impacts AI and A researchers, and tech companies) Progress within specific projects: F1: Cold hardiness prediction for frost mitigation (Grape, Sweet cherry) Installation of grape cold-hardiness models on AgWeatherNet. Multi-task learning models for both grape budbreak prediction and cherry cold-hardiness prediction. F2: Weather data imputation and forecasting algorithms for site-specific modeling and use A new generative diffusion model for time-series imputation that outperforms the previous state-of-the-art models. F3: Prediction of soil water content for deficit irrigation Design of a new neural net model for SWC, and preliminary tests showing promising long-term predictive capabilities F4: AI-enabled farm decision support tools Investigation of existing Ag simulators for AI decision support, which revealed that there are currently no simulators that appear appropriate for specialty crops. First version of benchmarks and paper submission for the OPCC problem. F5: Building topological tools for multi-cultivar spatio-temporal data Demonstrated that persistent homology barcodes can uncover inter-cultivar and inter-season relationships. Developed an interactive visualization tool to visually explore multi-season mult-cultivar data sets. F6: Temperature Inversion Prediction Developed a visualization to animate the temperature changes occurring at AgWeatherNet stations during a specified time period. Analyzed the relative usefulness of including certain AWN features, HRRR predictions and lag features for temperature inversion strength prediction F7: Robust model evaluation for geospatial problems Proof of a theoretical criterion for unbiased performance estimation in geospatial problems. A new cross-validation algorithm that addresses spatial autocorrelation and covariate shift. F8. Weather and crop physiology data enabled AI model for automated heat stress mitigation (Apple, Grape) Season-long crop and cultivar specific data is being collected in apple (cv. Honeycrisp, Cosmic Crisp) Preliminary model for apple FST prediction has been attempted, by an undergraduate intern, that is better than the existing modeling approach. L1: Human-robot collaborative tools and approaches for dormant fruit tree pruning Developed new Deep Learning models for tree-branch semantic segmentation and tree-branch instance segmentation. Created a new dataset of simulated, digital tree models (LPy systems) Developed a new computer vision algorithm for estimating the cross sectional area of tree trunks, and a new 'Follow the Leader Controller' for active visual scanning of trees. L2: Human-robot collaborative tools and approaches for fruit tree flower/blossom thinning New deep-learning models for early-stage flower and full-bloom flower cluster detection and segmentation, as well as flower density estimation, localization, and counting. A new electrically actuated end-effector with a brushing mechanism for robotic thinning. Developed an integrated robotic blossom thinning system and tested it in a commercial apple orchard W1: Agricultural Digital Twins (AgTwin) Deployed a new Agricultural Digital Twin for the state of Washington. W2: Orchard age prediction Recreated a method for predicting orchard age which uses the NDVI time series of an orchard. Employed AlexNet to classify fields as having a trellis or not W3: Canal/Waterway extraction and segmentation Built tools to visualize orchard shapes and waterways overlayed with RapidEye satellite images. Generated waterway ground truth images for all satellite images W4: Streamflow forecasting Finalized a new model which guarantees that every test-time prediction is consistent with the domain knowledge by utilizing a neuro-symbolic learning approach W5: Fallow prediction Analyzed the 2015 drought in Washington and developed a machine learning model for fallow prediction W6: A machine learning framework to explain complex geospatial simulations: A climate change case study Studied how snowmelt varies with climate variables W7: Attention-based transformer models for predicting snow water equivalent A new attention-based machine learning framework for SWE prediction
Publications
- Type:
Journal Articles
Status:
Accepted
Year Published:
2023
Citation:
You, Alexander, Nidhi Parayil, Josyula Gopala Krishna, Uddhav Bhattarai, Ranjan Sapkota, Dawood Ahmed, Matthew Whiting, Manoj Karkee, Cindy M Grimm, Joseph Davidson. Semi-autonomous precision pruning of upright fruiting offshoot cherry systems. IEEE Robotics and Automation Magazine.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2023
Citation:
Welankar, Sejal, Paola Pesantez-Cabrera, Bala Krishnamoorthy, Lynn Mills, Markus, Keller, Ananth Kalyanaraman. Persistent Homology to Study Cold Hardiness of Grape Cultivars. 2023 AAAI Workshop on Agriculture and Food Systems (AIAFS). https://openreview.net/pdf?id=PPoe26Ys-j.
- Type:
Journal Articles
Status:
Under Review
Year Published:
2023
Citation:
Wang, Jing, Laurel Hopkins, Tyler Hallman, W. Douglas Robinson, Rebecca Hutchinson. Cross-validation for Geospatial Data: Estimating Generalization Performance in Geostatistical Problems. Transactions on Machine Learning Research.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Wang, Tieqiao, Pico Sankari, Jostan Brown, Achyut Paudel, Liqiang He, Manoj Karkee, Ashley Thompson, Cindy Grimm, Joseph Davidson, and Sinisa Todorovic. 2023. Automatic Estimation of Trunk Cross Sectional Area Using Deep Learning. In Precision Agriculture, 49198. Wageningen Academic Publishers, 2023. https://doi.org/10.3920/978-90-8686-947-3_62.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2023
Citation:
Saxena, Aseem, Paola Pesantez-Cabrera, Rohan Ballapragada, Markus Keller, Alan Fern. Multi-Task Learning for Budbreak Prediction. 2023 AAAI Workshop on Agriculture and Food Systems (AIAFS).
https://openreview.net/pdf?id=kvGm8DJ-cM.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Parayil, Nidhi, Alexander You, Cindy Grimm, and Joseph Davidson. 2023. Follow the Leader: A Path Generator and Controller for Precision Tree Scanning with a Robotic Manipulator. In Precision Agriculture, 16774. Wageningen Academic Publishers.
https://doi.org/10.3920/978-90-8686-947-3_19.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Mishra, Ritwick, Stephen Eubank, Madhurima Nath, Manu Amundsen, and Abhijin Adiga. Community Detection Using Moore-Shannon Network Reliability: Application to Food Networks. In Complex Networks and Their Applications XI, 27182. Studies in Computational Intelligence. Cham: Springer International Publishing.
https://doi.org/10.1007/978-3-031-21131-7_21.
- Type:
Conference Papers and Presentations
Status:
Accepted
Year Published:
2023
Citation:
Khanal, Salik R., Ranjan Sapkota, Dawood Ahmed, Uddhav Bhattarai, Manoj Karkee. Machine Vision System for Early-stage Apple Flowers and Flower Clusters Detection for Precision Thinning and Pollination. IFAC World Congress, Yokohama, Japan.
- Type:
Other
Status:
Accepted
Year Published:
2023
Citation:
He, Liqian, Wei Wang, Albert Chen, Min Sun, Cheng-hao Kuo, Sinisa Todorovic. Bidirectional Alignment for Domain Adaptive Detection with Transformers. Amazon Science.
www.amazon.science/publications/bidirectional-alignment-for-domain-adaptive-detection-with-transformers.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2023
Citation:
Harrison, Galen, Amro Alabsi Aljundi, Jiangzhuo Chen, S.S. Ravi, Anil Kumar Vullikanti, Madhav V. Marathe, and Abhijin Adiga. Identifying Complicated Contagion Scenarios from Cascade Data. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 413545. KDD 23. New York, NY, USA: Association for Computing Machinery. https://doi.org/10.1145/3580305.3599841.
- Type:
Conference Papers and Presentations
Status:
Accepted
Year Published:
2023
Citation:
Hamid Md Montaser, Amreeta Chatterjee, Mariam Guizani, Andrew Anderson, Fatima Moussaoui, Sarah Yang, Isaac Tijerina Escobar, Anita Sarma, and Margaret Burnett. How to measure diversity actionably in technology . Equity, Diversity, Inclusion in Software Engineering
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2023
Citation:
Ghosh, Subhankar, Yuanjie Shi, Taha Belkhouja, Yan Yan, Jana Doppa, and Brian Jones. Probabilistically Robust Conformal Prediction. Proc. Uncertainty in Artificial Intelligence (UAI), 2023. https://openreview.net/forum?id=4xI4oaqIs2.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2023
Citation:
Ghosh Subhankar, Taha Belkhouja, Yan Yan, and Janardhan Rao Doppa. 2023. "Improving Uncertainty Quantification of Deep Classifiers via Neighborhood Conformal Prediction: Novel Algorithm and Theoretical Analysis." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 6: 772230. https://doi.org/10.1609/aaai.v37i6.25936.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2023
Citation:
Garcia, Rosalinda, Patricia Morreale, Lara Letaw, Amreeta Chatterjee, Pakati Patel, Sarah Yang, Isaac Tijerina Escobar, Geraldine Jimena Noa, and Margaret Burnett. Regular CS � Inclusive Design = Smarter Students and Greater Diversity. ACM Transactions on Computing Education. https://dl.acm.org/doi/10.1145/3603535.
- Type:
Journal Articles
Status:
Under Review
Year Published:
2023
Citation:
Fern, Alan, Margaret Burnett, Joseph Davidson, Janardhan Rao Doppa, Paola Pesantez-Cabrera, Ananth Kalyanaraman. AgAID Institute - AI for Agricultural Labor and Decision Support. AI Magazine.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Abatzoglou, John T., Daniel J. McEvoy, Nicholas J. Nauslar, Katherine C. Hegewisch, and Justin L. Huntington. Downscaled Subseasonal Fire Danger Forecast Skill across the Contiguous United States. Atmospheric Science Letters 24, no. 8: e1165. https://doi.org/10.1002/asl.1165.
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2024
Citation:
Thapa, Krishu, Bhupinderjeet Singh, Supriya Savalkar, Alan Fern, Kirti Rajagopalan, Ananth Kalyanaraman. Attention-based Models for Snow-Water Equivalent Prediction. Innovative Applications of Artificial Intelligence 2024.
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2024
Citation:
Kokten, Ozmen E., Raviv Raich, James Holmes, Alan Fern. Learning Extended Forecasts of Soil Water Content via Physically-Inspired Autoregressive Models. Innovative Applications of Artificial Intelligence 2024.
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2024
Citation:
Goebel, Kristen, Paola Pesantez-Cabrera, Markus Keller, Alan Fern. Transfer Learning via Auxiliary Labels for Cold-Hardiness Prediction. Innovative Applications of Artificial Intelligence 2024.
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2024
Citation:
Amine, Mohammed, Bhupinderjeet Singh, Jana Doppa, Kirti Rajagopalan, Ananth Kalyanaraman, Aryan Deshwal. Streamflow Prediction with Uncertainty Quantification for Water Management: A Neuro-Symbolic Learning Approach. 38th Annual AAAI Conference on Artificial Intelligence (Social Impact track).
- Type:
Conference Papers and Presentations
Status:
Accepted
Year Published:
2023
Citation:
Ferdousi, Tanvir, Mingliang Liu, Kirti Rajagopalan, Jennifer Adam, Abhijin Adiga, Mandy Wilson, S. S. Ravi, Anil Vullikanti, Madhav V. Marathe, Samarth Swarup. A Machine Learning Framework to Explain Complex Geospatial Simulations: A Climate Change Case Study. Proceedings of the Winter Simulation Conference.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Bertucci, Donald, Md Montaser Hamid, Yashwanthi Anand, Anita Ruangrotsakun, Delyar Tabatabai, Melissa Perez, and Minsuk Kahng. 2022. DendroMap: Visual Exploration of Large-Scale Image Datasets for Machine Learning with Treemaps. IEEE Transactions on Visualization and Computer Graphics 29, no. 1: 32030.
https://doi.org/10.1109/TVCG.2022.3209425.
- Type:
Journal Articles
Status:
Accepted
Year Published:
2023
Citation:
Belkhouja Taha, Yan Yan, Janardhan Rao Doppa. 2022. Out-of-Distribution Detection in Time-Series Domain: A Novel Seasonal Ratio Scoring Approach. ACM Transactions on Intelligent Systems and Technology (TIST). arXiv. https://doi.org/10.48550/arXiv.2207.04306.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2023
Citation:
Belkhouja, Taha, Dina Hussein, Ganapati Bhat, Jana Doppa. Energy-Efficient Missing Data Recovery in Wearable Devices: A Novel Search-based Approach. Proceedings of ISLPED 2023.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Belkhouja, Taha, and Janardhan Rao Doppa. Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features. Journal of Artificial Intelligence Research 73: 143571. https://doi.org/10.1613/jair.1.13543.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Belkhouja, Taha, Yan Yan, and Janardhan Rao Doppa. Dynamic Time Warping Based Adversarial Framework for Time-Series Domain. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, no. 6: 735366. https://doi.org/10.1109/TPAMI.2022.3224754.
|
Progress 09/01/21 to 08/31/22
Outputs
Target Audience: Students (K-12, associate degree programs, undergraduate, graduate) Postdoctoral researchers Faculty at all AgAID member organizations External research collaborators in academia and industry Specialty crop growers Specialty crop agricultural farm managers and workers Crop commissions and crop consultants Water irrigation districts State departments of agriculture and ecology K-12 educators Associate degree program and undergraduate program educators IT industry partners AgTech and FarmTech industry partners Federal funding agencies including USDA NIFA and NSF Population groups: Underrepresented minority groups including (but not limited to) Hispanic/Latinx and Native American First generation college students Underrepresented genders Changes/Problems:?There has been no change in the scope or objectives of the project. However there have been a few changes in project personnel and collaborative arrangements, and a few challenges in student recruitment. As noted above none of these changes have impacted our overall scope or objectives. We report on these changes for the sake of completeness in reporting. Changes in collaborative arrangements: IBM Research was originally listed as a subawardee in the original proposal and at project initiation. However after discussions with our IBM Research collaborators (and some personnel changes at their end), it has now been mutually agreed that: IBM Research will still continue to collaborate with our team but not as a subawardee; instead they will serve as unfunded collaborators; the work that they were originally planning to cover on their end with respect to forecasting (relevant for the Water intelligence thrust) will now be performed by our team at WSU; IBM Research will still continue to provide access and support to their IBM PAIRS platform to ensure all objectives of our collaboration are met. This does not change the scope of the project. This change was relayed to the NIFA National Program Leader and has been approved. Changes in senior personnel: There have been a few changes in project personnel, in particular owing to faculty retirement or departures. Senior Personnel David Brown at WSU left academia for industry. His role in the original proposal was as a co-lead for the Farm intelligence thrust. He has been replaced by Lav Khot who is also Co-PI on the project. Co-PI Khot has also taken over as the AgWeatherNet Director, a role that was previously held by David Brown. Senior Personnel Claudio Stockle has retired and is no longer on the budget. He continues to serve as an unfunded collaborator in Emeritus Faculty status. His original role was in the Farm intelligence thrust and his responsibilities have been taken over by other senior personnel on the thrust (Markus Keller and Troy Peters). Senior Personnel Amit Dhingra has moved from WSU to Texas A&M University. Dhingra had only a minor role in technology adoption at a consulting capacity. He continues to hold an adjunct faculty role at WSU and will operate as an unpaid collaborator in the following years. COVID-19 related hiring and event challenges: There were a combination of hiring challenges and visa delays induced by COVID-19 on students and postdoctoral researchers. As the timing of the start of the award is not synchronized with the start of the semester, we have unexpended funds from year 1. However almost all of those activities have been initiated. Additionally, due to continued impacts on travel from the COVID-19 pandemic, some events were postponed or switched to virtual/hybrid events and as such, changed the original plans for events/travel in Year 1. What opportunities for training and professional development has the project provided?The AgAID Institute contributed to the training and professional development of a variety of individuals. A summary of the numbers by the different categories is presented below. Please note that the reported numbers represent a lower bound on the number of trainees. For names and areas of the individuals involved please refer to the detailed annual review report submitted to the cognizant NIFA National Program Leader. 4 postdoctoral scholars 43 graduate (PhD or MS) students 8 resident undergraduate students 14 summer undergraduate research interns How have the results been disseminated to communities of interest? Publications/papers: Abatzoglou, John, Daniel J. McEvoy, Nicholas J. Nauslar, Katherine C. Hegewisch, Justin L. Huntington. 2022. "Downscaled subseasonal fire danger forecast skill across the contiguous United States". Atmospheric Science Letters. (Submitted) Bertucci, Donald, Md Montaser Hamid, Yashwanthi Anand, Anita Ruangrotsakun, Delyar Tabatabai, Melissa Perez, and Minsuk Kahng. 2022. "DendroMap: Visual Exploration of Large-Scale Image Datasets for Machine Learning with Treemaps." IEEE Transactions on Visualization and Computer Graphics. arXiv. https://doi.org/10.48550/arXiv.2205.06935. (Accepted) Chatterjee, Amreeta, Lara Letaw, Rosalinda Garcia, Doshna Umma Reddy, Rudrajit Choudhuri, Sabyatha Sathish Kumar, Patricia Morreale, Anita Sarma, and Margaret Burnett. 2022. "Inclusivity Bugs in Online Courseware: A Field Study." In Proceedings of the 2022 ACM Conference on International Computing Education Research - Volume 1, 356-72. ICER '22. New York, NY, USA: Association for Computing Machinery. https://doi.org/10.1145/3501385.3543973. (Published) Dodge, Jonathan, Andrew A. Anderson, Matthew Olson, Rupika Dikkala, and Margaret Burnett. 2022. "How Do People Rank Multiple Mutant Agents?" In 27th International Conference on Intelligent User Interfaces, 191-211. IUI '22. New York, NY, USA: Association for Computing Machinery. https://doi.org/10.1145/3490099.3511115. (Published) Dodge, Jonathan, Roli Khanna, Jed Irvine, Kin-ho Lam, Theresa Mai, Zhengxian Lin, Nicholas Kiddle, et al. 2021. "After-Action Review for AI (AAR/AI)." ACM Transactions on Interactive Intelligent Systems 11 (3-4): 29:1-29:35. https://doi.org/10.1145/3453173. (Published) Guizani, Mariam, Igor Steinmacher, Jillian Emard, Abrar Fallatah, Margaret Burnett, and Anita Sarma. 2022. "How to Debug Inclusivity Bugs? A Debugging Process with Information Architecture." In 2022 IEEE/ACM 44th International Conference on Software Engineering: Software Engineering in Society (ICSE-SEIS), 90-101. IEEE Computer Society. https://doi.org/10.1109/ICSE-SEIS55304.2022.9794009. (Published) Homayouni, Taymaz, Akram Gholami, Arash Toudeshki, Leili Afsah-Hejri, and Reza Ehsani. 2022. "Estimation of Proper Shaking Parameters for Pistachio Trees Based on Their Trunk Size." Biosystems Engineering 216 (April): 121-31. https://doi.org/10.1016/j.biosystemseng.2022.02.008. (Published) Kalyanaraman, Ananth, Margaret Burnett, Alan Fern, Lav Khot, and Joshua Viers. 2022. "Special Report: The AgAID AI Institute for Transforming Workforce and Decision Support in Agriculture." Computers and Electronics in Agriculture 197 (June): 106944. https://doi.org/10.1016/j.compag.2022.106944. (Published) Khanna, Roli, Jonathan Dodge, Andrew Anderson, Rupika Dikkala, Jed Irvine, Zeyad Shureih, Kin-Ho Lam, et al. 2022. "Finding AI's Faults with AAR/AI: An Empirical Study." ACM Transactions on Interactive Intelligent Systems 12 (1): 1:1-1:33. https://doi.org/10.1145/3487065. (Published) Kokel, Harsha, Nikhilesh Prabhakar, Balaraman Ravindran, Erik Blasch, Prasad Tadepalli, and Sriraam Natarajan. 2022. "Hybrid Deep RePReL: Integrating Relational Planning and Reinforcement Learning for Information Fusion." In 2022 25th International Conference on Information Fusion (FUSION), 1-8. https://doi.org/10.23919/FUSION49751.2022.9841246. (Published) Koul, Anurag, Mariano Phielipp, and Alan Fern. 2022. "Offline Policy Comparison with Confidence: Benchmarks and Baselines." Transactions on Machine Learning Research. arXiv. https://doi.org/10.48550/arXiv.2205.10739. (Submitted) Saxena, Aseem, Paola Pesantez-Cabrera, Rohan Ballapragada, Kin-Ho Lam, Alan Fern, Markus Keller. 2023. " Grape Cold Hardiness Prediction via Multi-Task Learning". AAAI Conference on Artificial Intelligence. (Submitted) You, Alexander, Cindy Grimm, and Joseph R. Davidson. 2022. "Optical Flow-Based Branch Segmentation for Complex Orchard Environments." IEEE/RSJ International Conference on Intelligent Robots and Systems. arXiv. https://doi.org/10.48550/arXiv.2202.13050. (Accepted) You, Alexander, Nidhi Parayil, Josyula Gopala Krishna, Uddhav Bhattarai, Ranjan Sapkota, Dawood Ahmed, Matthew Whiting, Manoj Karkee, Cindy M. Grimm, and Joseph R. Davidson. 2022. "An Autonomous Robot for Pruning Modern, Planar Fruit Trees." IEEE Robotics and Automation Letters. arXiv. https://doi.org/10.48550/arXiv.2206.07201. (Submitted) Welankar, Sejal, Paola Pesantez-Cabrera, Ananth Kalyanaraman. 2022. "Extracting patterns in cold hardiness data using topological data analysis." Fourth International Workshop on Machine Learning for Cyber-Agricultural Systems (MLCAS2022). (Submitted) Saxena, Aseem, Paola Pesantez-Cabrera, Rohan Ballapragada, Kin-Ho Lam, Alan Fern, Markus Keller. 2022. "Grape Cold Hardiness Prediction via Multi-Task Learning." Fourth International Workshop on Machine Learning for Cyber-Agricultural Systems (MLCAS2022). (Submitted) Presentations: Ag2PI Field Day. Iowa State University INNOVATE'21. US Highbush Blueberry Council Integrative Precision Agriculture seminar. University of Georgia DnC2S meeting series. Oak Ridge National Laboratory North Central Washington Tree Fruit Granville Seminar. Pacific Northwest National Lab OSU Cherry Day 2022. OSU Extension Indigo Ag Science Seminar Series Tech Talk Tuesday School of EECS, Oregon State University International EUGAIN Summer Training School, Universita? della Svizzera italiana Summer Seminar Series IoT4Ag California Water Commission NCW TECH Alliance & North Central Educational Service District AI World Congress: AI x Agriculture: The New Era in Agriculture Other outreach events: NexTech Robotics 2021 SWE Conference Expanding your Horizons Tri-County Innovation Fair FLY CITRIS Drone Day Merced County Office of Education STEAM Festival Bobcat Summer STEM Academy What do you plan to do during the next reporting period to accomplish the goals?Farm Intelligence Projects F1: Cold hardiness prediction for frost mitigation Improve machine learning models and deploy them under practical settings Evaluate decision support interfaces and considerations F2: Weather data imputation and forecasting algorithms for site-specific modeling and use Design a spatio-temporal imputation mechanism that takes offline data from multiple weather stations in AgWeatherNet and imputes all missing sensor data. Design imputation approaches for predicting rest of the season weather data F3: Prediction of soil water content for deficit irrigation Develop and test machine learning models Compare and validate models with ground-truth obtained from Demo farm (smart vineyard) Obtain requirements for decision support interfaces F4: Policy comparison with uncertainty estimation using offline data Expand the benchmarks to include some Ag-inspired domains. Develop new offline policy comparison approaches that improve on the current metrics. Identify applications within the scope of AgAID decision support and apply F5: Building a topological data analytical framework for multi-cultivar spatio-temporal data Develop topological models and representation for frost mitigation and AWN data sets Apply and test topological models and incorporate with machine learning workflows Labor Intelligence Projects L1: Automated tree fruit pruning Identify pruning rules, workflow, and interface opportunities identified/developed to date Integrate developed rule set into robot arm pruning algorithms Conduct second phase human study to test/evaluate in the field L2: Automated flower thinning Understand human thinning decision making, developing thinning rules from formative studies Revise prototype, testing, crop yield, and quality analysis Improve deep learning models for individual flower detection L3: Mechanical harvesting in pistachios Analyze data collected from sensors for mechanical harvest Identify parameters for operator control and harvest tree manipulation Develop models for recommending optimal parameter settings for mechanical harvest Water Intelligence Projects W1: Streamflow forecasting Integrate domain knowledge into the graph neural network model for generating consistent predictions Develop methods for uncertainty quantification and large-scale empirical evaluation Expand into human influenced watersheds Explore alternative machine learning methodologies to model the forecast problem W2: Fallow prediction Improve the machine learning models for fallow prediction Expand to include information from California Conduct other extensions including estimating field age, prediction of fallowed fields under various drought scenarios, identifying changes in crop mixes, etc. W4: Detection of potential large-scale shifts in agricultural yields due to climate change Develop models to identify phase shift boundaries in the parameter space of VIC-CropSyst using active learning W5: IBM seasonal forecasts Conduct thorough comparative evaluation of accuracy of commercial seasonal forecast products available via the IBM PAIRS platform. Cross-cutting Research Projects Demo farm Continue and complete instrumentation of the two Demo farm sites (WSU Prosser and WVC) Use Demo farm sites for research thrust data collection and ground truthing Use Demo farm sites for training including boot camps and undergraduate research experience Human-AI workflows Develop and implement Ag use-case specific human-AI design workflows Apply and test inclusivity and interactability metrics Education Continue to train graduate and undergraduate students, and mentor postdoctoral scholars for research Conduct AgAID summer undergraduate research internships Conduct Digital Agathon Recruit students into PhD and MS degree programs in AI and in digital agriculture related topics Conduct MESA field trip and refine curriculum based on survey results Extension and workforce development Continue conducting learning circles for various research thrusts and to include new stakeholder interactions Continue extension activities for workforce training and broadening participation Broadening participation Pilot AgAID training/curriculum materials into HOEEP program to train current workforce Mentor students under LSAMP program Conduct bilingual training and outreach
Impacts
What was accomplished under these goals?
Major activities: Launched the AgAID Institute in September 2021, including Institute website and project kickoff Initiated and launched multiple projects under research and multiple activities for broader impact and broadening participation Established communication channels and shared repositories and resources for collaboration Established project tracking and reporting systems Generated and conducted thrust level meetings and project level meetings for project initiation and implementation Worked with the external evaluation team to create and implement evaluation plan Received regular input and feedback from internal executive council for strategic decisions and Institute implementation Drafted and maintained Institute Strategic & Implementation Plan including authorship guidelines, EAB charter, IRB, and timelines and milestones Conducted the first cohort of summer undergraduate research interns Initiated stakeholder engagement and collaborations Initiated Institute level collaborations with external entities including industry and international partners Established the first cohort of External Advisory Board Specific objectives for ongoing work: In Year 1, we have initiated and have made progress across all research thrusts and broader impact thrusts. All projects are ongoing and in what follows, we list the set of objectives where work was initiated and where there has been significant progress. These objectives are listed by the different active projects ongoing under these different thrusts or across thrusts. Farm Intelligence Projects F1: Cold hardiness prediction for frost mitigation Develop machine learning models for grape cold hardiness prediction and compare those to existing models Develop and evaluate multi-task learning methods for cold hardiness of different grape cultivars F2: Weather data imputation and forecasting algorithms for site-specific modeling and use Develop and implement weather station correlation methodology for site-specific usage Exploration of robust weather data imputation methods and evaluate them on AgWeatherNet F3: Prediction of soil water content for deficit irrigation Determine variables of interest for prediction F4: Policy comparison with uncertainty estimation using offline data Development of methods for offline policy comparison F5: Building a topological data analytical framework for multi-cultivar spatio-temporal data Define topological data analysis workflows to capture multi-cultivar behavior in cold hardiness Labor Intelligence Projects L1: Automated tree fruit pruning Develop strategies and criteria for automated pruning through formative studies Investigate workflows and interfaces to effectively integrate robot pruning systems into existing farm workflows L2: Automated flower thinning Investigate/acquire manual operation and expert knowledge to develop strategies for flower thinning Investigate various deep learning models for detecting and locating flowers, and estimating flower cluster orientation and flower density L3: Mechanical harvesting in pistachios Installation of sensors to measure and map how individual trees are being shaken by different operators Water Intelligence Projects W1: Streamflow forecasting Combine the benefits of domain knowledge in the form of physics-based models and spatiotemporal graph neural networks to improve the overall prediction accuracy and uncertainty quantification W2: Fallow prediction Develop and evaluate ML models based on satellite time-series data for fallow prediction W3: Satellite data assimilation into the VIC model Improve the VIC hydrology model's ability to capture key snow and soil moisture processes by assimilating satellite imagery Cross-cutting Research Projects Demo farm Identify Demo farm sites at WSU (vineyard and apple orchard) and equip them with field sensors, imaging devices, drones, and field robots Identify a commercial orchard near WVC for a second Demo farm site, and install continuous plant monitoring sensors Human-AI workflows Design of interactive and inclusive human-AI workflows that allow for incorporation of human behavior and diversity of target groups Education Train graduate and undergraduate students, and mentor postdoctoral scholars for research Conduct AgAID summer undergraduate research internships and train 14 students Plan for Digital Agathon Initiate PhD and MS degree programs in AI Develop curricular materials for MESA field trip for middle school Extension and workforce development Implement extension activities to inform and contribute to research including learning circles and stakeholder interactions Initiate extension activities for workforce training and broadening participation Broadening participation Prepare and participate in Hispanic Orchard Employee Education Program Mentor students under LSAMP program Conduct bilingual training and outreach Work with MESA program to develop curriculum for computer science field trip to our Demo farm Significant results achieved: Ag-inspired AI research Development of cold hardiness predictive models for frost mitigation in grapes Formative studies to guide extraction of rules governing apple tree pruning Application of machine learning to develop predictive models for Ag land fallowing due to drought Foundational AI research Foundations for multi-task learning Developing the foundations for socio-economic mag Representation learning and science-guided ML for forecasting Cross-thrust integration Initiation of research projects and use-case prioritization Development of instrumented Demo farm at two sites for research and training Establish online portals and resources for intra-team training Establish data and modeling workflows and evaluation of computational platforms for research use Education Interdisciplinary training and tutorials in AI and Digital Ag Development of K-12 curricular materials for middle schoolers including NextTech robotics Research experience for undergraduates with inter-generational mentoring ?AI Expo aimed at educators at a STEM summit organized by NCW Tech Alliance and NCESD Initiation of PhD and MS in AI program at OSU Development of curricular materials for the first AgAID sponsored Digital AgAthon in partnership with Microsoft Extension and workforce development Learning circles and formative studies with Ag user groups, policy makers, and Hispanic community Preliminary studies for workforce training in orchard management Field days in orchard management (including in Spanish) Broadening participation and diversity Various K-12 training and outreach activities in Hispanic rural CA including coding camps and robotics programs Field day for K-12 MESA to Yakama Nation middle schoolers Recruitment and training of diverse groups as part of graduate and undergraduate research training Multi-organizational synergies/achievements Engagement with hitech and AgTech industry Outreach and presentations at various partner events including (but not limited to) Ag2PI, IoT4Ag, U.S. Highbush blueberry commission annual meeting, and SAS annual PD meeting Communication and securing infrastructure support from commissions Expansion of research into other specialty crops (berries, potatoes) Knowledge transfer Published or submitted at least 15 peer-reviewed papers and presented at numerous venues Training and orientation for AgAID Institute participants in intellectual property and commercialization Impact of the institute as a nexus point for collaborative efforts Establish a coordination and collaboration network with other sister NIFA AI Institutes (AIFARMS, AIFS, AIIRA) Establish communication with other NSF AI Institutes Initiate international collaborations (with Australia, Chile, and Netherlands) as part of the NSF-NIFA AI Institutes International Collaboration Supplements program Explore partnerships with the Cascadia Innovation Corridor and with Amazon AWS Key outcomes or other accomplishments realized: none to report yet
Publications
- Type:
Journal Articles
Status:
Under Review
Year Published:
2022
Citation:
Abatzoglou, John, Daniel J. McEvoy, Nicholas J. Nauslar, Katherine C. Hegewisch, Justin L. Huntington. 2022. Downscaled subseasonal fire danger forecast skill across the contiguous United States . Atmospheric Science Letters.
- Type:
Journal Articles
Status:
Accepted
Year Published:
2022
Citation:
Bertucci, Donald, Md Montaser Hamid, Yashwanthi Anand, Anita Ruangrotsakun, Delyar Tabatabai, Melissa Perez, and Minsuk Kahng. 2022. DendroMap: Visual Exploration of Large-Scale Image Datasets for Machine Learning with Treemaps. IEEE Transactions on Visualization and Computer Graphics. arXiv. https://doi.org/10.48550/arXiv.2205.06935.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2022
Citation:
Chatterjee, Amreeta, Lara Letaw, Rosalinda Garcia, Doshna Umma Reddy, Rudrajit Choudhuri, Sabyatha Sathish Kumar, Patricia Morreale, Anita Sarma, and Margaret Burnett. 2022. Inclusivity Bugs in Online Courseware: A Field Study. In Proceedings of the 2022 ACM Conference on International Computing Education Research - Volume 1, 35672. ICER 22. New York, NY, USA: Association for Computing Machinery. https://doi.org/10.1145/3501385.3543973.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2022
Citation:
Dodge, Jonathan, Andrew A. Anderson, Matthew Olson, Rupika Dikkala, and Margaret Burnett. 2022. How Do People Rank Multiple Mutant Agents? In 27th International Conference on Intelligent User Interfaces, 191211. IUI 22. New York, NY, USA: Association for Computing Machinery. https://doi.org/10.1145/3490099.3511115.
- Type:
Journal Articles
Status:
Published
Year Published:
2021
Citation:
Dodge, Jonathan, Roli Khanna, Jed Irvine, Kin-ho Lam, Theresa Mai, Zhengxian Lin, Nicholas Kiddle, et al. 2021. After-Action Review for AI (AAR/AI). ACM Transactions on Interactive Intelligent Systems 11 (34): 29:1-29:35. https://doi.org/10.1145/3453173.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2022
Citation:
Guizani, Mariam, Igor Steinmacher, Jillian Emard, Abrar Fallatah, Margaret Burnett, and Anita Sarma. 2022. How to Debug Inclusivity Bugs? A Debugging Process with Information Architecture. In 2022 IEEE/ACM 44th International Conference on Software Engineering: Software Engineering in Society (ICSE-SEIS), 90101. IEEE Computer Society. https://doi.org/10.1109/ICSE-SEIS55304.2022.9794009
- Type:
Journal Articles
Status:
Published
Year Published:
2022
Citation:
Homayouni, Taymaz, Akram Gholami, Arash Toudeshki, Leili Afsah-Hejri, and Reza Ehsani. 2022. Estimation of Proper Shaking Parameters for Pistachio Trees Based on Their Trunk Size. Biosystems Engineering 216 (April): 12131. https://doi.org/10.1016/j.biosystemseng.2022.02.008.
- Type:
Journal Articles
Status:
Published
Year Published:
2022
Citation:
Kalyanaraman, Ananth, Margaret Burnett, Alan Fern, Lav Khot, and Joshua Viers. 2022. Special Report: The AgAID AI Institute for Transforming Workforce and Decision Support in Agriculture. Computers and Electronics in Agriculture 197 (June): 106944. https://doi.org/10.1016/j.compag.2022.106944.
- Type:
Journal Articles
Status:
Published
Year Published:
2022
Citation:
Khanna, Roli, Jonathan Dodge, Andrew Anderson, Rupika Dikkala, Jed Irvine, Zeyad Shureih, Kin-Ho Lam, et al. 2022. Finding AIs Faults with AAR/AI: An Empirical Study. ACM Transactions on Interactive Intelligent Systems 12 (1): 1:1-1:33. https://doi.org/10.1145/3487065.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2022
Citation:
Kokel, Harsha, Nikhilesh Prabhakar, Balaraman Ravindran, Erik Blasch, Prasad Tadepalli, and Sriraam Natarajan. 2022. Hybrid Deep RePReL: Integrating Relational Planning and Reinforcement Learning for Information Fusion. In 2022 25th International Conference on Information Fusion (FUSION), 18. https://doi.org/10.23919/FUSION49751.2022.9841246.
- Type:
Journal Articles
Status:
Under Review
Year Published:
2022
Citation:
Koul, Anurag, Mariano Phielipp, and Alan Fern. 2022. Offline Policy Comparison with Confidence: Benchmarks and Baselines. Transactions on Machine Learning Research. arXiv. https://doi.org/10.48550/arXiv.2205.10739.
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2023
Citation:
Saxena, Aseem, Paola Pesantez-Cabrera, Rohan Ballapragada, Kin-Ho Lam, Alan Fern, Markus Keller. 2023. " Grape Cold Hardiness Prediction via Multi-Task Learning". AAAI Conference on Artificial Intelligence.
- Type:
Conference Papers and Presentations
Status:
Accepted
Year Published:
2022
Citation:
You, Alexander, Cindy Grimm, and Joseph R. Davidson. 2022. Optical Flow-Based Branch Segmentation for Complex Orchard Environments. IEEE/RSJ International Conference on Intelligent Robots and Systems. arXiv. https://doi.org/10.48550/arXiv.2202.13050.
- Type:
Journal Articles
Status:
Under Review
Year Published:
2022
Citation:
You, Alexander, Nidhi Parayil, Josyula Gopala Krishna, Uddhav Bhattarai, Ranjan Sapkota, Dawood Ahmed, Matthew Whiting, Manoj Karkee, Cindy M. Grimm, and Joseph R. Davidson. 2022. An Autonomous Robot for Pruning Modern, Planar Fruit Trees. IEEE Robotics and Automation Letters. arXiv. https://doi.org/10.48550/arXiv.2206.07201.
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2022
Citation:
Welankar, Sejal, Paola Pesantez-Cabrera, Ananth Kalyanaraman. 2022. Extracting patterns in cold hardiness data using topological data analysis. Fourth International Workshop on Machine Learning for Cyber-Agricultural Systems (MLCAS2022).
- Type:
Conference Papers and Presentations
Status:
Under Review
Year Published:
2022
Citation:
Saxena, Aseem, Paola Pesantez-Cabrera, Rohan Ballapragada, Kin-Ho Lam, Alan Fern, Markus Keller. 2022. Grape Cold Hardiness Prediction via Multi-Task Learning. Fourth International Workshop on Machine Learning for Cyber-Agricultural Systems (MLCAS2022).
|