Progress 06/01/23 to 05/31/24
Outputs
Target Audience:AI-Climate reached a broad audience of stakeholders, students, and industry experts during Y1. Our Extension and Workforce Development team specifically implemented many stakeholder engagement activities, including needs assessments, literature reviews, focus groups, and iPad surveys, laying the groundwork for impactful outreach and education efforts.In year 1 alone, their focus group efforts have involved over 50 farmers, foresters, and non-farmer stakeholders across six states. In our research and collaboration endeavors, we actively engage scholars from underrepresented groups through various avenues, including research experiences for undergraduate and graduate students, mentorship programs to establish long-term relationships, and research initiatives addressing equity in AI-CLIMATE adoption. Currently, 19 students across various levels and backgrounds are engaged in bi-weekly mentorship, research, and literature review circles facilitated by AI-Climate faculty. Additionally, at Prairie View A&M University (PVAMU), graduate students in computer science were provided with a GitHub site giving access to KGML code and datasets associated with the AI-CLIMATE publication by Liu et al. (2024). Graduate students were able to learn how to run KGML code and use datasets to reproduce all of the key findings in the AI-CLIMATE publication, providing them with insights into both computer science methodology as well as real world results pertaining to effects of autotrophic and heterotrophic respiration on carbon sequestration. The Broadening Participation Team (BP) has not only amplified outreach efforts to underserved audiences but also significantly informed the work of AI-CLIMATE with representation across most of the EWD work. Presentations at key events, including the Rutgers Climate Symposium 2023 and Breaking Barriers Through Diversity and Inclusivity 2024 in Islamabad, Pakistan, have been opportunities to showcase our dedication to diversity and inclusivity while shaping the direction of our initiatives. At the Rutgers Climate Symposium, Dr. Rose Ogutu delivered presentations and moderated sessions including "AI Climate Broadens Outreach to Underserved Audiences," and "AI Green Alliance" underscored how BP members actively contribute to shaping global dialogues and collaborations within the AI-CLIMATE community. Additionally, AI-CLIMATE team members also engaged externally with several USDA funded Climate Smart Commodity projects to identify potential collaborations with AI-CLIMATE on tracking CSAF practice implementation and developing tools for Monitoring, Reporting and Verification of carbon sequestration and greenhouse gas emissions associated with practice implementation. Changes/Problems:The convergent research and other activities of AI-CLIMATE are largely on track or ahead of schedule. However, due to trainee availability and membership bandwidth, we did push out milestones around Computer Vision Guided Perception Analysis and Integration research activities into Q1 of Year 2. We also found that some of the initiatives or milestones that require or would be best supported by a fully-staffed and mature Institute have been slower to start and will require additional attention to ensure timely progress. To that end, AI-CLIMATE is in the end stages of hiringadditional staff members to work exclusivelyon furthering our education and outreach initiatives. What opportunities for training and professional development has the project provided?Providing basic internal training on AI, climate, and team science concepts is a cornerstone of our institute going into Year 2. We plan to address challenges regarding uncertainties about roles, responsibilities, and understanding of key concepts such as climate and AI. Implementing basic training sessions will ensure that all participants have a shared understanding of these complex concepts, fostering clearer communication and alignment of goals within the Institute. That said, we did take many opportunities during our Year 1 All-Hands Meetings to share knowledge across specialties and vignettes. These sessions provided opportunities for team members to collaborate, ask questions, and provide a basis of understanding across the institute, which then led smaller groups to undertake their own additional training to fill in any perceived gaps in training and knowledge. For example, members of the EWD team took courses on artificial intelligence, statistics, and leadership courses. This group also participated in Bruce Erickson's digital agriculture course as a means to educate themselves while simultaneously providing feedback. AI-CLIMATE has undertaken a series of mentorship and training activities during year 1 in the aim of fostering academic and personal growth in students interested in undertaking careers related to AI-CLIMATE. Natalie Hunt has worked on developing a AI/CSAF modules for undergrad students to train the next generation of CSAF leaders, while Emma Eckley, Candace Hulbert, and Bruce Erickson have all invited students to assist with their work on climate smart practices as interns and mentees. In addition, faculty members David Mulla and Nikos Papanikolopoulos facilitate a bi-weekly KGML student meeting, which includes a journal club readings, mentor presentations, and discussions based on the research interests of student members. Currently, 22 students and postdocs participate in the bi-weekly meeting. Our stakeholder engagement objectives focus on conducting needs assessments to gather insights, experiences, and challenges faced by stakeholders. We employ various methods such as face to face meetings, literature reviews, focus groups, surveys, and engaged research to inform the development of AI-driven decision support tools and technologies. In our annual report, we highlight our team and institute's coordinated efforts in advancing our mission. We've established efficient communication channels such as Slack, Trello, and Zotero to facilitate collaboration and resource sharing. Our Google Drive houses essential documents, agendas, and meeting notes, ensuring transparency and accessibility. Weekly team meetings serve as a platform for progress updates and strategic planning. In our stakeholder engagement and needs assessment initiatives, we've developed a comprehensive plan to gather insights and address key concerns. Our literature review is currently underway, laying the foundation for informed decision-making. Plans for focus groups with extension groups are in progress, with pilot Farmer Focus Group meetings having been conducted in New York and Minnesota during April 2024. Additionally, we're conducting pilot surveys to gather valuable feedback from farmers and stakeholders. In terms of training and education, we're committed to developing curriculum and providing instruction in critical areas such as CSAF, digital agriculture, and AI technology integration in agriculture. As an example, Graduate students at Prairie View A&M University (PVAMU), a Historically Black College and University (HBCU) received training on how to use KGML-ag code and sample datasets. Our outreach efforts encompass speaking engagements, conferences, and events are tailored for farmers. We're actively engaging with younger audiences through initiatives like the June 2024 NYS 4-H Career Expo, offering interactive sessions on AI and CSA. Furthermore, we're enhancing stakeholder engagement through updated website content, informative flyers, and collaboration with design consultants to create engaging materials. In our stakeholder engagement and needs assessment initiatives, we've developed a comprehensive plan to gather insights and address key concerns. Our literature review is currently underway, laying the foundation for informed decision-making. Plans for focus groups with extension groups are in progress, with pilot Farmer Focus Group meetings having been conducted in New York and Minnesota during April 2024. Additionally, we're conducting pilot surveys to gather valuable feedback from farmers and stakeholders. In terms of training and education, we're committed to developing curriculum and providing instruction in critical areas such as CSAF, digital agriculture, and AI technology integration in agriculture. Education on Digital Agriculture and Climate-Smart Agriculture: Climate-Smart Agriculture Course for Farmers (Live training by Zoom with office Hours) - Led by Cornell University - Team members (Allison Chatrchyan and Candace Hulbert) developed a new course on Climate Smart Agriculture, with the USDA Northeast Climate Hub, for dairy farmers and advisors in NY, VT, PA and ME, through the Dairy Climate Adaptation. We developed and implemented a 7 week course, and will be supporting dairy farmers and their advisors to develop a climate adaptation or mitigation plan for their farm. Candace Hulbert also worked with the USDA Climate Adaptation and Mitigation Fellowship (CAMF) to present her new On-Farm Disaster Preparedness and Planning module to northeastern and midwestern Women and Non-binary Vegetable growers and northeastern Diversified Agriculture and Agroforestry farmers. These modules can also be used for additional training with AI-climate Institute stakeholders. We will also offer a supplemental training on Digital Agriculture and AI for all of the USDA NE CAMF farmer fellows (https://www.adaptationfellows.net) Digital Agriculture Online Course for Advisors (asynchronous) - Led by Purdue University - in development, to be offered by Fall 2024 GHG Mitigation Training Sessions using COMET-Farm - Led by Colorado State University Development of new modules by our team - in development during Year 2. In terms of training and education, collaborative efforts with institutions like Purdue, Cornell, Colorado State, and Delaware State will lead to the development and offering of sessions on CSA, climate-smart tools, and AI. These sessions aim to provide practical training and hands-on experiences for farmers and stakeholders. For example, on March 8, 2024, Candace Hulbert presented to fifty livestock and vegetable farmers at the Profiting From a Few Acres Conference in Dover Delaware about Understanding Climate-Smart Agriculture Strategies and Technologies on Small Farms. Our outreach and engagement efforts involve active participation in agriculture meetings, conferences, and events, coupled with the development of materials and content to effectively engage with stakeholders. This includes updating our website, creating informative one-pagers authored by research team members, and refreshing our AI-Institute logo with the assistance of a design consultant. These initiatives collectively underscore our commitment to advancing agricultural innovation and fostering meaningful engagement with stakeholders. How have the results been disseminated to communities of interest?AI-CLIMATE has undertaken a series of approaches to raise awareness of its mission and share our findings. During Year 1, our faculty created two new graduate-level courses to be taught in the fall of 2024, which will integrate AI-CLIMATE content. We have also made our research datasets available to Prairie View A&M University for students. David Mulla presented two very well-received talks on AI tools being developed by AI-CLIMATE at the USDA-funded AI for Ag conference organized by Texas A&M and Prairie View A&M Universities in April of 2024. The event was attended by over 250 faculty members, graduate students, farmers, and government agency representatives. The Education and Workforce Development team has beencoordinating an AI-CLIMATE Stakeholder Needs Assessment to collect the views, experiences, and challenges and opportunities relevant stakeholders face to inform the development of new AI-driven decision support tools and technology. The needs assessment included a literature review of multiple stakeholder views on CSAF, digital agriculture, and AI; focus groups conducted in 6 states NY, DE, CO, IN, MN and CA; and national stakeholder survey of farmer and rancher views on CSAF, digital agriculture, and AI. The focus groups included six farmer and rancher focus groups (in-person); three forester focus groups (in-person); six extension focus groups (in-person); one Climate-Smart Commodities leader focus group (on-line); and one state and federal agency staff focus group (on-line). Furthermore, Allison and Candace from the EWD team are project leaders and content developers for the Climate Adaptation and Mitigation Fellowship, which runs four programs that began in January 2024 and will run through the beginning of 2026. These cohort-based learning opportunities are for farmers and agricultural advisors in the Northeast and Midwest who are interested in climate change adaptation and mitigation strategies and planning, as well as peer-to-peer networking and support. Candace then partnered with Rose Ogutu to facilitate the Profiting From A Few Acres Conference in March of 2024, which provides small farm owners with best practices concerning agriculture production, farm management, and profitability. Each of these events served as a platform for publicizing the work done at AI-CLIMATE to a wide and diverse audience. AI-CLIMATE has held a weekly All-Hands Meeting starting September 20th, 2023, focused on knowledge sharing of research, education, outreach, and extension activities. Each meeting set aside time for questions, collaboration, and conceptualization to foster community and synthesize efforts. On average, AI-CLIMATE has had 20-30 participants per meeting. Midwestern Climate Smart Commodity Projects Presentation: David Mulla Date: 12/13/2023 Summary: David Mulla's presentation provides an overview of initiatives and challenges related to Climate-Smart Commodity practice implementation, carbon accounting, and renewable energy development in the agricultural and energy sectors. It discusses the GEVO Climate-Smart Farm-to-Flight Program and collaborative efforts between Climate Smart Commodity projects and AI-CLIMATE to advance tracking of practice implementation and monitoring, reporting and verification. Interactive Exploration of High Dimensional Water Quality Data At Scale Presentation: Shrideep Pallickara Date: 1/10/2024 Summary: The presentation introduces the aQua Tool, which facilitates the interactive exploration of high-dimensional water quality data. It covers spatial trends, Clean Water Act violations, census data correlations, and environmental and agricultural concerns. The tool supports data analysis related to the Clean Water Act, provides insights into water quality recommendations, and integrates various data types for comprehensive analysis. The Sustain project, Digital Twins, and compliance with the EPA's Clean Water Act are also discussed. Earth Economy Modeling Presentation: Justin Johnson Date: 1/17/2024. Summary: The presentation discusses GTAP-InVEST, a model integrating global trade analysis with ecosystem service assessment. It highlights the impact of land-use change on agriculture, biodiversity, and carbon storage, emphasizing the tradeoffs between conservation and agricultural expansion. The importance of policy optimization for sustainable development is underscored, suggesting the evaluation of tradeoff frontiers to balance economic and environmental objectives. Nature Comm. Paper on KGML Presentation: Licheng Liu, Zhenong Jin and Vipin Kumar Date: 1/24/2024. Summary: The presentation introduces the KGML-ag-Carbon architecture for enhancing carbon cycle quantification in agroecosystems. It utilizes Gated Recurrent Unit (GRU) models and synthetic data to improve model performance and fine-tune predictions. The presentation also discusses the extrapolation of the model to the US Corn Belt region and outlines future directions for incorporating management practices into the framework. Education for Digital Agriculture and AI Presentation: Bruce Erickson Date: 1/31/2024 Summary: This presentation covers the integration of digital technologies into agriculture education, focusing on AI, data science, remote sensing, and GIS. It discusses educational programs at various levels and emphasizes the importance of practical, hands-on learning to meet the demands of digital agriculture. Challenges and strategies for teaching advanced topics are also addressed. Optimization Theory Presentation: Mingyi Hong Date: 2/7/2024 Summary: The presentation explores advancements in optimization theory and its applications to AI-CLIMATE in machine learning, signal processing, and information processing. It discusses algorithms for solving complex optimization problems, the synergy between learning and reasoning, and the integration of deep learning techniques for optimizing physical systems.Overview of New Advances in Land Carbon Cycle Modeling Workshop Presenter: Yiqi Luo Date: 2 /14/2024. Summary: This presentation provides an overview of recent advancements in land carbon cycle modeling, focusing on biogeochemical neural networks (BINN), computational ecology, big data science, and machine learning techniques. It discusses matrix approaches, machine learning tools, data assimilation techniques, and interdisciplinary collaboration in advancing ecosystem modeling. Panel Discussion: Data Needs for Carbon Sequestration and Greenhouse Emissions Modeling Presentation Panel: Soil Carbon and GHG-Yiqi Luo, Dominic Woolf; Soil Moisture-Shrideep Pallickara, Sangmi Lee Pallickara; GEMS-Kevin Silverstein Date: 2/21/2024. Summary: The presentations highlight data needs for understanding carbon sequestration and greenhouse emissions. They emphasized the importance of detailed, well labeled, spatially standardized and accessible datasets and metadata for research in this field, with a focus on soil health, cover crop performance, and ecosystem services. Adaptation and Forest-Crop Transitions and Collaborative Project Discussion Presentation: Chad Babcock Date: 2/28/2024. Summary: The presentation discusses approaches to enhancing forest carbon maps for climate change mitigation and carbon markets. It covers estimation methods, the NASA Carbon Monitoring System project, methods for enhancing Forest Inventory and Analysis (FIA) data, AI technologies, and challenges faced by landowners in initiating carbon projects. Modeling and Mapping Soil Organic Carbon Sequestration Presentation: Dominic Woolf Date: 3/4/2024 What do you plan to do during the next reporting period to accomplish the goals?Research: Develop enhanced/accelerated algorithms to optimize modeling AI modeling to improve accuracy of forest carbon estimation and mapping Extend the application of BINN, KGML-ag, beyond the realm of soil organic carbon. Develop, train and test SVPNet for soil moisture mapping Incorporate accelerated models/AI-models into decision support tools Education: Host a National Workforce Development Workshop in partnership with industry stakeholders and other AI Institutes Design a new graduate course on Geospatial AI (to be taught from Fall 2024, NCSU) Create AI-Climate specializations in current degree programs Develop new industry-driven curricula for Ag/ Food/ Sustainability industry with community colleges and universities Partner with industry subject matter experts to create modules that can be dropped into existing courses to accelerate CSAF workforce readiness Partner with South Dakota State University to integrate climate-smart and AI chapters into a new 2nd edition Precision Agriculture textook Partner with one USDA NextGen Program awardee to build on existing climate-smart ag and forestry engagements such as providing internships to students Develop a secondary education curriculum for high school students designed to introduce high school students to digital agriculture through engaging, hands-on COMET-based activities. Stakeholder Engagement: Interview farmers and various stakeholders to understand the usage and knowledge of AI in agriculture and forestry Develop a survey paper with survey and focus group results on AI knowledge of agriculture and forestry stakeholders Develop a new professional development course on agronomy and AI For KGML, specifically focused on the following next steps: To improve the accuracy of KGML, the group identified a need to develop benchmark datasets that include both experimental and synthetic data. Key variables such as nitrous oxide would be included. Enhancements are underway in the nitrification and denitrification routines within the DayCent model. Additionally, there is a focus on addressing spatio-temporal variability in soil moisture modeling within KGML. Reducing Uncertainty in National Assessment Inventory by more accurately estimating C and GHG fluxes. This flagship project aims to reduce uncertainty in the National Assessment Inventory using KGML tools, which will concurrently improve the accuracy of the COMET PLANNER. The approach should involve developing AI guided tools for reducing uncertainty, model intercomparison (Ecosys, DNDC, DayCent), ensemble modeling (E.g. Land-CRAFT project) and surrogate modeling. Foundational LLM Modeling The project involves foundational modeling with pre-training tasks and predefined weights. Improvements in achieving these weights have been demonstrated in crop mapping and can be extended to estimating carbon, nitrous oxide, methane fluxes, and the implementation of climate-smart practices. A matrix approach to modeling C, N, and P fluxes is proposed as a new element of foundational modeling. Linking Top-Down and Bottom-Up Modeling This project aims to link top-down and bottom-up modeling for nitrous oxide and methane using tall tower and eddy covariance measurements. The goal is to bridge gaps between these approaches to verify and improve accuracy in the National Inventory. Developing an accurate KGML-DayCent model is crucial for this project, indicating that it will require time to achieve.
Impacts
What was accomplished under these goals?
In its inaugural year, AI-CLIMATE has embarked on a mission to revolutionize AI and decision support tools for climate-smart practices in agriculture and forestry, aiming to tackle previously insurmountable challenges and expedite climate change adaptation and mitigation efforts while informing policy and bolstering carbon markets. Our vision encompasses cultivating a national and global community of AI experts and practitioners, establishing ourselves as a trusted entity capable of delivering impactful science-based solutions in collaboration with partners worldwide. Ultimately, our institute is focused on engaging with farmers, foresters, industry experts, and non-profits to address the interactions between goals such as agricultural production, GHG mitigation, increasing adaptation to climate change impacts, enhancing environmental quality, and promoting rural and urban prosperity equitably. Research: Our research teams made advances in compiling benchmark data sets to be used both in future research, as well as in educational settings. The KGML team has recorded over 2000 observations across 178 experiments around the globe, and has shared these findings with courses being taught at the University of Minnesota and Prairie View A&M University. The KGML group published 5 scientific papers, gave more than 10 technical presentations, mentored 7 graduate students and postdocs, and applied for 1 provisional patent. The Climate Risks, Forest-Ag Adaptation group completed ~50% of their benchmark dataset across three separate models and designed two new graduate courses for North Carolina State University and the University of Minnesota in the Fall of 2024. Furthermore, they have initiated collaborative efforts with the Central America and Mexico Coniferous Resources Cooperative. All of these accomplishments supported the vision of AI-CLIMATE to foster collaboration across broad stakeholders. Education and workforce development (EWF): The flagship project for the EWF team in Year 1 was creating and implementing the Stakeholder Needs Assessment. This tool focuses on understanding the requirements of farmers, advisors, partners, and policymakers for integrating AI-infused tools into farm decision-making processes. The goal is to reduce greenhouse gas (GHG) emissions, enhance climate change adaptation, and foster synergies within the AI-Climate research team through continuous stakeholder engagement. Team members (Allison Chatrchyan and Candace Hulbert) developed a new course on Climate Smart Agriculture, with the USDA Northeast Climate Hub, for dairy farmers and advisors in NY, VT, PA and ME, through the Dairy Climate Adaptation. We developed and implemented a 7 week course, and will be supporting dairy farmers and their advisors to develop a climate adaptation or mitigation plan for their farm. Additionally, Candace Hulbert also worked with the USDA Climate Adaptation and Mitigation Fellowship (CAMF) to present her new On-Farm Disaster Preparedness and Planning module to northeastern and midwestern Women and Non-binary Vegetable growers and northeastern Diversified Agriculture and Agroforestry farmers. These modules can also be used for additional training with AI-climate Institute stakeholders. Additionally, we assisted with the development of the Digital Agriculture Online Course for Advisors (asynchronous) - Led by Purdue University - in development, to be offered by Fall 2024 Broadening Participation (BP)- At the Black Farmers Conference in Delaware State University, held on November 9, 2023, Bruce Erickson, delivered a presentation titled "Agriculture Technology Trends and Need to Know," addressing crucial developments in the field. This event, coordinated by Rose Ogutu, provided valuable insights into technological advancements in agriculture. Similarly, at the Profiting from a Few Acres Conference in Dover, Delaware, on March 8, 2024, our speaker, Candace Hulbert, presented on "Understanding Climate-Smart Agriculture Strategies and Technologies on Small Farms." Coordinated by Rose Ogutu, Gulnihal Ozbay, and Allison Chatrchyan, this conference focused on empowering small-scale farmers with knowledge about climate-smart agricultural practices. Our participation in these conferences underscores our commitment to staying at the forefront of agricultural innovation and knowledge dissemination. At the Rutgers Climate Symposium 2023, held at Rutgers, New Brunswick, NJ, on November 15, 2023, Rose Ogutu, delivered a compelling presentation titled "AI Climate Broadens Outreach to Underserved Audiences." Coordinated by Rose Ogutu, Gulnihal Ozbay, and Allison Chatrchyan, this symposium highlighted the innovative use of AI technology to extend outreach efforts to underserved communities, contributing to greater inclusivity in climate initiatives. Furthermore, at the Breaking Barriers Through Diversity and Inclusivity 2024 event in Islamabad, Pakistan, on March 27, 2024, Rose Ogutu served as the session moderator. The session focused on the "AI Green Alliance," emphasizing collaborative efforts towards sustainability and environmental conservation. Coordinated by Rose Ogutu and Gulnihal Ozbay, this event showcased our commitment to promoting diversity, inclusivity, and global cooperation in addressing environmental challenges. Graduate students at Prairie View A&M University (PVAMU), a Historically Black College and University (HBCU), received training on how to use KGML-ag code and sample datasets. David Mulla presented two very well-received talks on AI tools being developed by AI-CLIMATE at the USDA-funded AI for Ag conference organized by Texas A&M and Prairie View A&M Universities in April of 2024 and attended by over 250 faculty members, graduate students, farmers, and government agency representatives. Collaboration and Knowledge Transfer- AI-CLIMATE has held a weekly All-Hands Meeting starting September 20th, 2023 focused on knowledge sharing of research, education, outreach, and extension activities. On average, AI-CLIMATE has had 20-30 participants per meeting. Each meeting included a presentation and discussion on research, education and workforce development, and broadening participation. Based on feedback from our All-Hands Meetings, the Nexus leads then devised a roadmap for achieving the Nexus milestones identified in the SIP, cognizant of the dependencies involved in these Nexus activities. The roadmap includes a co-creation kickoff, an Intellectual Exchange Platform Launch, I-Corps Curriculum Integration, and the formation of an Industry Consortium.
Publications
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Liu, L., Zhou, W., Guan, K., et al. (2024). Knowledge-guided machine learning can improve carbon cycle quantification in agroecosystems. Nature Communications, 15, 357.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Luo, Y., Tao, T., Huang, Y. Y., Hungate, B. A., Manzoni, S., Frey, S. D., Schmidt, M. W. I., Reichstein, M., Carvalhais, N., Ciais, P., Jiang, L. F., Lehmann, J., Wang, Y. P., Houlton, B. Z., Ahrens, B., Mishra, U., Hugelius, G., Hocking, T. D., Lu, X. J., Shi, Z., Viatkin, K., Vargas, R., Yigini, Y., Omuto, C., Malik, A. A., Peralta, G., Cuevas-Corona, R., Di Paolo, L. E., Luotto, I., Liao, C. J., Liang, Y. S., Saynes, V. S., Huang, X. M., & Luo, Y. Q. (2023). Microbial carbon use efficiency promotes global soil carbon storage. Nature, 618, 981985.
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Al-Amin, A. K. M., Lowenberg?DeBoer, J., Erickson, B. J., Evans, J. T., Langemeier, M. R., Franklin, K., & Behrendt, K. (2024). Economics of strip cropping with autonomous machines. Agronomy Journal, 118.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Davis, C. L., Bai, Y., Chen, D., Robinson, O., Ruiz-Gutierrez, V., Gomes, C. P., & Fink, D. (2023). Deep learning with citizen science data enables estimation of species diversity and composition at continental extents. Ecology.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Emick, E., Babcock, C., White, G. W., Hudak, A. T., Domke, G. M., & Finley, A. O. (2023). An approach to estimating forest biomass while quantifying estimate uncertainty and correcting bias in machine learning maps. Remote Sensing of Environment, 295, 113678.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Erickson, B., & Lowenberg-DeBoer, J. (2023). Precision Agriculture Dealership Survey Results. CropLife Magazine. Department of Agricultural Economics and Department of Agronomy, Purdue University.
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Grimson, M., Almeida, R., Shi, Q., Bai, Y., Angarita, H., Siqueira Pacheco, F., Schmitt, R., Flecker, A., & Gomes, C. P. (2024). Scaling Up Pareto Optimization for Tree Structures with Affine Transformations: Evaluating Hybrid Floating Solar-Hydropower Systems in the Amazon. Proceedings of the AAAI Conference on Artificial Intelligence, 38(20), 22067-22075.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Guan, K., Jin, Z., Peng, B., Tang, J., DeLucia, E.H., West, P.C., Jiang, C., Wang, S., Kim, T., Zhou, W. and Griffis, T., 2023. A scalable framework for quantifying field-level agricultural carbon outcomes. Earth-Science Reviews, 243, p.104462.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Jayaprakash, B., Eagon, M., Yang, M., Northrop, W., & Shekhar, S. (July 2023). Towards Carbon-Aware Spatial Computing: Challenges and Opportunities. Institute for Geospatial Understanding through an Integrative Discovery Environment (I-GUIDE) Forum
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Johnson, J. A., Baldos, U. L., Corong, E., Hertel, T., Polasky, S., Cervigni, R., Roxburgh, T., Ruta, G., Salemi, C., & Thakrar, S. (2023). Investing in nature can improve equity and economic returns. Proceedings of the National Academy of Sciences, 120(27), e2220401120
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
K?l?�, D. K., & U?ur, �. (2023). Hybrid wavelet-neural network models for time series. Applied Soft Computing, 144, 110469.
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Kira, O., Wen, J., Han, J., McDonald, A., Barrett, C.B., Ortiz-Bobea, A., Liu, Y., You, L., Mueller, N. and Sun, Y., 2024. A scalable crop yield estimation framework based on remote sensing of solar-induced chlorophyll fluorescence (SIF). Environmental Research Letters.
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Kumar, V., Steinbach, M., Chatterjee, S., Lindsay, K., 2024. Prescribed Fire Modeling using Knowledge-Guided Machine Learning for Land Management. SDM24 Best Application Paper Award.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Lin, Y., & Chiang, Y.Y. (2023). Modeling Spatially Varying Physical Dynamics for Spatiotemporal Predictive Learning. In Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL '23) (pp. 111). Association for Computing Machinery.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Mathers, C., Black, C. K., Segal, B. D., Gurung, R. B., Zhang, Y., Easter, M. J., Williams, S., Motew, M., Campbell, E. E., Brummitt, C. D., Paustian, K., & Kumar, A. A. (2023). Validating DayCent-CR for cropland soil carbon offset reporting at a national scale. Geoderma, 438, 116647.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Min, Y., Bai, Y., & Gomes, C. P. (2023). Unsupervised Learning for Solving the Travelling Salesman Problem. Advances in Neural Information Processing Systems, 36, 47264-47278.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Min, Y., Chang, M.-C., Kong, S., Gregoire, J. M., van Dover, R. B., Tompson, M. O., & Gomes, C. P. (2023). Physically Informed Graph-based Deep Reasoning Net for Efficient Combinatorial Phase Mapping. 22nd International Conference on Machine Learning and Applications (ICMLA).
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Ogle, S. M., Breidt, F. J., Del Grosso, S., Gurung, R., Marx, E., Spencer, S., Williams, S., & Manning, D. (2023). Counterfactual scenarios reveal historical impact of cropland management on soil organic carbon stocks in the United States. Scientific Reports, 13(1), 14564.
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Ravirathinam, P., Ghosh, R., Khandelwal, A., Jia, X., Mulla, D., & Kumar, V. (2024). Combining Satellite and Weather Data for Crop Type Mapping: An Inverse Modeling Approach. In Proceedings of the 2024 SIAM International Conference on Data Mining (SDM) (pp. 445-453)
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Shrideep, & Pallickara, S., Matin, A., Khandelwal, P., Pallickara, S. L., & Pallickara, S. (2023). Discern: Leveraging Knowledge Distillation to Generate High Resolution Soil Moisture Estimation from Coarse Satellite Data. In Proceedings of the IEEE International Conference on Big Data (IEEE BigData), Sorento, Italy.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Shrideep, & Pallickara, S., Young, M., Pallickara, S. L., & Pallickara, S. (2023). aQua: A Framework for Spatiotemporal Analysis and Visualizations of Water Quality Data at Scale. In Proceedings of the IEEE International Conference on Big Data (IEEE BigData), Sorento, Italy.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Shrideep, & Pallickara, S., Warushavithana, M., Barram, K., Mitra, S., Carlson, C., Ghosh, S., Breidt, J., Pallickara, S. L., & Pallickara, S. (2023). A Framework for Profiling Spatial Variability in the Performance of Classification Models. In Proceedings of the IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT).
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Shrideep, & Pallickara, S., Mitra, S., Young, M., Pallickara, S. L., & Pallickara, S. (2023). Rubiks: Rapid Explorations and Summarization over High Dimensional Spatiotemporal Datasets. In Proceedings of the IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT).
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Shrideep, & Pallickara, S., Mitra, S., Khandelwal, P., Pallickara, S., & Pallickara, S. (2023). Argus: Rapid Tracking of Wildfires from Unlabeled Satellite Images. In Proceedings of the IEEE International Conference on Cloud Computing (CLOUD), Chicago, USA.
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Stewart, A. J., Halabisky, M., Babcock, C., et al. (2024). Revealing the hidden carbon in forested wetland soils. Nature Communications, 15(1), 726.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Tao, F., Huang, Y., Hungate, B.A., Manzoni, S., Frey, S.D., Schmidt, M.W., Reichstein, M., Carvalhais, N., Ciais, P., Jiang, L. and Lehmann, J., 2023. Microbial carbon use efficiency promotes global soil carbon storage. Nature, 618(7967), pp.981-985.
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Wang, Y., Kong, S., Gregoire, J. M., & Gomes, C. P. (2024). Conformal Crystal Graph Transformer with Robust Encoding of Periodic Invariance. Proceedings of the 38th AAAI Conference on Artificial Intelligence.
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Yang, Q., Liu, L., Zhou, J., Ghosh, R., Peng, B., Guan, K., Tang, J., Zhou, W., Kumar, V., & Jin, Z. (2023). A flexible and efficient knowledge-guided machine learning data assimilation (KGML-DA) framework for agroecosystem prediction in the US Midwest. Remote Sensing of Environment, 299.
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Karpatne, A., Xiaowei Jia, X., Kumar, V. (2024). Knowledge-guided Machine Learning: Current Trends and Future Prospects. arXiv:2403.15989.
|