Progress 04/01/24 to 03/31/25
Outputs
Target Audience:The target audience has expanded from primarily PERSEUS research and development teams to external professionals within forestry and natural resource management fields for professional development and continuing education credits. Efforts have included forestry stakeholder workshops on drones for forest data acquisition and processing collected data through the D2S platform. UGA's expanding Online Learning in Applied Forestry (OLAF) free course offerings, including remote sensing and geographic information systems, are focused towards forestry professionals for continuing education credit and the general public engaged with forest science. This has been particularly focused on forestry professionals from the national forest system of the south, based on work with the Talladega National Forest. Purdue's summer 2025 Digital Data Acquisition Camp (DDAC) in-person short course, an immersive hand-on camp encompassing four graduate-level credits, is geared towards current professionals working in natural resources fields. This course integrates UAS operations, photogrammetric and LiDAR methods of forest measurements, and environmental sensor networks and IoT for forest ecosystem management. The Digital Ecology and Natural Resources (DENR) professional master's degree program will incorporate the DDAC as well as eight additional credits on more in-depth data acquisition techniques, 12 credits on GIS, three credits on ethics and six credits of an independent study capstone project. The iForester smartphone application is available to the general public, providing forestry professionals and other interested stakeholders with an accessible tool for preliminary forest inventory knowledge. Presently 988 users across the world have downloaded the application. Changes/Problems:Change: The University of Georgia Warnell School of Forestry and Natural Resources has added Dr. Stephen Kinane, Assistant Professor of Silviculture, and Dr. Sheng-I Yang, Assistant Professor of Forest Biometrics, as non-funded collaborators to PERSEUS. What opportunities for training and professional development has the project provided?Task 4.1 Learning Communities: Purdue offered two semesters of a Digital Forestry Vertically Integrated Projects (VIP) undergraduate course. Purdue convened two terms of mechanical engineering senior undergraduate students engaged in improving the BackPack LiDAR systems, which incorporated learning about the unique environment of collecting data in forested areas. Purdue convened a group of six first-semester graduate students on the topics of beginning research and successfully launching in graduate school. Fall term PERSEUS graduate student meetings included guest speakers from UMaine and UGA who shared their research, career journeys and perspectives on academic work. A questionnaire on professional development activities was again given to PERSEUS graduate students in January 2025. This survey assessed interest in topics and delivery methods for professional development activities. These activities were then developed and became the focus of the spring meetings focused on professional development topics such as "Managing your online research presence" and "The academic publishing process 101." The academic publishing learning module was developed to help familiarize PERSEUS students with the stages involved in publishing a peer-reviewed paper, and offered in spring 2025.All meetings provided a chance for students to ask questions and share challenges or success stories. Five nonthesis UGA Master of Forest Resources graduate students (not funded by PERSEUS) assisted in the development of a South-wide GIS databases (e.g., roads, streams, soils, ownership). Task 4.2 Interns and Fellows: The Summer 2024 cohort of PERSEUS undergraduate interns consisted of 11 Purdue undergraduate students who completed mentored research projects under the guidance of PERSEUS faculty. Cohorts met at least weekly to discuss progress on their research and a variety of professional development topics. Interns presented their research at Purdue's 2024 annual Institute for Digital Forestry retreat. The program was summarized in a document hosted on the Purdue PERSEUS webpage (https://ag.purdue.edu/digital-forestry/projects/perseus/index.html). Six UGA interns were onboarded to assist with Objective 1 activities (wood bark image collection and database management as well as virtual reality (VR) capabilities and video library), Objective 2 (modeling) and Objective 4 (Online Learning in Applied Forestry [OLAF] AI course development). Postdoctoral research fellow trainings included one UMaine fellow in development and implementation of Delphi technique; one UMaine fellow in group techniques for decision-making, collaborative research, survey design and systematic literature reviews; one Purdue fellow on survey sampling, mail survey development, and mail survey administration, as well as Delphi method; and one UMaine fellow in group techniques for decision-making. Postdoctoral research fellows and graduate students formed a working group to draft manuscripts and provide feedback among each other. Professional development activities for early career scientists encouraged collaboration across institutions. Task 4.3 Curriculum Development: UMaine's big data Enhanced Forest Inventory and Analysis course was delivered in Spring 2024 for a mix of on-campus graduate students and postgraduates in the forestry workforce. This hybrid course used various modes of learning, including asynchronous video content (produced in collaboration with UMaine's Center for Innovation in Teaching and Learning), synchronous in-class discussions of conceptual materials, and guided hands-on data analysis exercises that demonstrated applications of the forestry "big data" concepts and methods. Students completed both independent projects (including Arduino sensor systems) and group work with multi-temporal remote sensing data. Students both reinforced and advanced their knowledge and practice of forest inventory approaches, from traditional ground-based plot networks to enhanced methods that incorporate remote sensing and ML models. The course included both independent and group projects and featured guest lectures on FIA. This is a core course of the UMaine School of Forest Resources' newly developed graduate certificate program. Professionals earned continuing education credits for both Maine's state forester license and toward national SAF accreditation. The course is part of UMaine's new graduate certificate program and is offered every other year. The course has been updated and refined with input received from the broader PERSEUS team. Two all-day hands-on technology workshops were held during the summer PERSEUS annual meeting at UMaine and at the Purdue Digital Forestry annual meeting. The workshop included hands-on experience with UAS platforms, recommendations and discussion from experienced UAS experts, and a demonstration of data processing and visualization using the Data to Science (D2S) platform. The UMaine workshop had nine facilitators and was attended by 23 participants, including two undergraduate and four graduate students, five faculty/staff and 12 local external stakeholders (e.g., Maine Forest Service). The Purdue workshop had eight facilitators and was attended by 13 participants, including four Purdue graduate students or postdoctoral research fellows and nine local external stakeholders (e.g., Indiana DNR, other university Extension). A short technology demonstration and discussion titled "Advances in Digital Forestry" was held at the 2024 annual SAF meeting in Loveland, Colorado. This included an update on the various forest inventory methods and metrics produced using digital tools and technologies. Attendees at the demonstration and discussion included forest managers from across the country, researchers from various universities and representatives from private industry. Purdue will pilot a Digital Data Acquisition Camp (DDAC) in Summer 2025. This immersive, hands-on camp will occur over three weeks and consist of four graduate-level credits. This course integrates UAS operations, photogrammetric and LiDAR methods of forest measurements, and environmental sensor networks and IoT for forest ecosystem management. Purdue's Digital Ecology and Natural Resources (DENR) professional master's degree program is working through the university approvals process. DENR will incorporate the DDAC as well as eight additional credits on more in-depth data acquisition techniques, 12 credits on GIS, three credits on ethics and six credits of an independent study capstone project. Task 4.4 Online Certificate: New modules were added to UGA's OLAF courses on remote sensing and artificial intelligence. Continuing education credits will be certified by SAF. DENR professional master's at Purdue will include online and residential pathways to accommodate working professionals as well as traditional graduate students. Post-docs and grad students formed a working group to draft manuscripts and provide feedback amongst each other. Encouraged by leads and lead by students. Professional development activity for early career scientists encouraging collaboration across institutions. The "Managing your online research presence" learning module that was developed in Year 1 was again offered to PERSEUS students in Spring 2025. The module focused on the use of online tools like Google Scholar profiles and ORCiD to track/manage research-related activities. How have the results been disseminated to communities of interest? Two all-day hands-on technology workshops were held during the summer PERSEUS annual meeting at UMaine and at the Purdue Digital Forestry annual meeting. The workshop included hands-on experience with UAS platforms, recommendations and discussion from experienced UAS experts, and a demonstration of data processing and visualization using the D2Splatform. The UMaine workshop had nine facilitators and was attended by 23 participants, including two undergraduate and four graduate students, five faculty/staff and 12 local external stakeholders (e.g., Maine Forest Service). The Purdue workshop had eight facilitators and was attended by 13 participants, including four Purdue graduate students or postdoctoral research fellows and nine local external stakeholders (e.g., Indiana DNR, other university Extension). A short technology demonstration and discussion titled "Advances in Digital Forestry" was held at the 2024 annual SAF meeting in Loveland, Colorado. This included an update on the various forest inventory methods and metrics produced using digital tools and technologies. Attendees at the demonstration and discussion included forest managers from across the country, researchers from various universities and representatives from private industry. Dissemination to the scientific community and interested public stakeholders includes 21 publications and over 30 presentations at professional and public conferences and workshops (see Products section). What do you plan to do during the next reporting period to accomplish the goals?Task 1.1 iForester: Efforts will focus on seamlessly integrating tree height and AI segmentation algorithms, as well as incorporating tree grading algorithms to determine commercial log and biomass values. Iterations of the species classification algorithm based on tree surface vein patterns and size data will continue along with additional acquisition of southern forest tree species images to help train tree species identification. Task 1.2 StemMapper: Improvements in UAV and BackPack systems TEAM efficiency will ensure alignment with large area LiDAR coverage from legacy geospatial data and airborne systems. BackPack trajectory improvements in data acquisition efficiency will follow a three-stage strategy: real time optimized path planning using collected BackPack data without the need for prior/external map data, or using UAV map data for off-line optimized trajectory designs coupled with real-time navigation for either relying on the onboard GNSS/INS unit, or relying on collected BackPack and UAV map data. Linking image and LiDAR data for improved trajectory enhancement and mapping will encompass more complete information for tree species identification. Identification will be augmented by integrating RGB/LiDAR and hyperspectral data from the high-altitude/wide-area coverage airborne systems. Task 1.3 Data Coverage: The ME biomass map_v1 will be published including a detailed documentation in the Oak Ridge National Laboratory Distributed Active Archive Center (DAAC)and a thorough description of the methods, data processing workflows, and data uncertainties. Subsequent versions will incorporate multiple LiDAR datasets, such as GEDI (Global Ecosystem Dynamics Investigation), G-LiHT (Goddard's LiDAR, Hyperspectral & Thermal Image), and additional 3DEP airborne LiDAR data, leveraging multi-temporal data for annual estimates and offering new insights into interannual variability and long-term forest dynamics. Improved models will be developed for estimating biomass, volume, basal area, and species groups for less intensively managed and natural pine-hardwood forests of the Piedmont area based on Talladega National Forest data. Models will include woody debris and fuel loads for less intensively managed upland pine-hardwood systems of the South, integrating field measurements with GEDI data for broad scale estimation. BackPack/UAV/high-altitude geospatial data will be integrated to generate accurate alignment of high-resolution data/products for enhancement of high-altitude/wide-area coverage airborne data. Task 2.1 Landowner optimization: IN and ME forest health site data will be collected in spring/summer, including proximal and UAV hyperspectal measurements, standard leaf functional trait analyses, forest stand health assessments, community composition and DBH. Task 2.2 Broad simulation: The existing LANDIS + Extensions model framework and analyses will be updated and expanded to include resilience impacts and habitat suitability. LANDIS input requirements and potential outcomes will be assessed in Southern and Midwest forests for broad-scale modeling. The ME Harvest Choice Model will be expanded, particularly IN and GA using State-specific data. The timber supply model focusing on forecasting prices, supply, and forest structure will be refined and work will begin on integration into PERSEUS information systems. Variables include FIA forest attributes stumpage price, land value, ownership, conservation status, and distance from mills and highways. Emphasis will be on producing a fully operational model. The Tree Planning LLM system will be enhanced for the ability to edit and design greenspaces and urban forests. The existing database will be expanded with geospatial urban forestry data derived from satellite imagery. Urban tree inventories will prioritize the refinement of forest tree crown localization and species extraction using a temporal approach incorporating seasonal and repeat imagery to enhance segmentation accuracy under variable lighting, occlusion, and phenological conditions. Parallel efforts will focus on browser-based scaling accessibility and usability while continuing to facilitate dissemination of actionable data. Task 2.4 Data Visualization: New data products will be added to the STAC repository, with those required for Tasks 2.1 and 2.2 prioritized. Task 3.1 Stakeholder Perceptions: Surveys and focus groups will be conducted to finalize the sampling frame for state-level data collection from stakeholders. These may include: Forestry professionals informed by the Delphi method and/or informed by landowners; Landowners informed by landowner focus groups and/or interviews; Business owners; and Technology needs and adoption, such as landowner interest in UAV certification, to understand potential educational opportunity needs. Task 3.2: Scenario development: Management approaches will be assessed based on landowner typology to feed into the scenario framework with initial findings through stakeholder and general perception survey analysis. Typologies will be determined by linking ownership and regional socio-economic and FIA plot data to estimate forest management and harvest decisions over the previous 20 years. Assessment of the model and scenario framework developed by UMaine will be continued and expanded to all three regions. Task 3.3 Focused Outreach: A target audience outreach strategy will be developed with prototype materials and workshops based on key project plans and updated findings. The materials will be trialed with representative stakeholders, iterated, and disseminated through strategic outlets with solicited input from key stakeholders. Task 3.4 Technology Application: Successful adoption of new technologies relies heavily on meeting stakeholder needs and providing meaningful training opportunities. We will continue to identify key stakeholders and their needs to improve offerings. This will entail developing detailed plans for training and soliciting input from other PERSEUS objective teams. We will finalize training opportunities and disseminate to strategic outlets, followed by soliciting feedback on training events and refinement iterations. An Extension specialist will be hired (Purdue) and dedicated to outreach activities; evaluating stakeholder digital technologies and assessing facilitators and barriers to adoption. Task 4.1 Learning communities: We will continue to engage engineering students in the design and building of the Backpack lidar systems. Task 4.2 Interns and fellows: A second cohort of PERSEUS undergraduate summer interns will be recruited at Purdue to complete mentored research projects in Summer 2025. Applications for these positions are being evaluated. Task 4.3 Curriculum development: UMaine has begun developing a graduate level course "Unoccupied Aerial Systems in the Forest Environment", which will provide training in small Unoccupied Aircraft Systems (sUAS) for aerial surveys in support of forestry and related natural resource applications. The course will include a combination of hands-on field work and computer-based activities. The course is expected to be offered in fall 2025. Purdue's DENR Professional Master's degree program plan of study will continue to be refined and new courses added as they are identified. Task 4.4 Online certificate: UMaine's big data in forestry course, "Enhanced Forest Inventory and Analysis" will continue forward as an every-other-year offering at UMaine, to be delivered next in Spring term 2026. Course development will continue in Year 3, notably with an emphasis on incorporating new data sets collected and technical workflows developed in the PERSEUS project. Specific examples include additional modules and training on the use of proximal sensing (i.e., terrestrial and UAV LiDAR) for forest inventory and monitoring. UGA will continue to develop new OLAF modules and refine existing modules.
Impacts
What was accomplished under these goals?
Task 1.1 iForester: Enhanced AI-based algorithms significantly improved segmentation accuracy for the height module. Using mobile Segment Anything Modeling (SAM), 547 of 562 trees were segmented with over 97% accuracy. For height, results demonstrated an error margin within 1 foot for the first 16-foot log. iForester DBH and height measures were used to initiate hardwood tree scaling, grading and pricing modules (Doyle, Scribner and International scales) for traditional standing tree board foot volume. A significant number of southern forest species were imaged to inform tree identification. The iForester smartphone application is publicly available, providing forest professionals and others with an accessible tool for preliminary forest inventory knowledge. Presently 988 users have downloaded the application. Task 1.2 StemMapper: User feedback integrated into the proximal (BackPack) system design includes the adoption of a less-expensive GNSS/INS position and orientation system, facilitating expedited processing and derivation of system position and orientation (trajectory or path). A new LiDAR sensor with more spinning beams and higher pulses per second yielded derived point clouds with higher point density and level of detail. Similar LiDAR design improvements to the near proximal (UAV) system yielded more spinning beams and higher pulses per second. A benchmarking UAV system with more precise GNSS/INS and LiDAR was developed to evaluate derived point cloud quality as well as forest inventory biometrics. BackPack point cloud generation algorithms Integrated Scan Simultaneous Trajectory Enhancement and Mapping (IS2-TEAM) and Generalized Trajectory Enhancement and Mapping (G-TEAM)were refined using acquired point clouds in natural and plantation forests in IN, ME, GA and AL. To improve UAV trajectory quality, the G-TEAM algorithm was modified to mitigate the impact of lower quality GNSS/INS trajectory for missions in areas with poor distribution of GNSS satellite constellation and longer distances to reference stations. UAV and BackPack images and LiDAR data integration resulted in more tractable species identification and process augmentation to improve the quality of the BackPack TEAM. Forest inventory pipeline algorithms were developed for full automation and straightforward implementation by low-experience users with early adopter feedback improving the user experience in deriving forest biometrics. Task 1.3 Data coverage: The ME statewide biomass map was updated using forest inventory data to calibrate a TensorFlow-based machine learning (ML) model that interprets 3D point clouds acquired by USGS 3DEP airborne LiDAR. FIA measurements were employed to calibrate stand growth models and normalize biomass estimates to reflect conditions in 2023. Wall-to-wall LiDAR-based mapping efforts were calibrated and validated at Howland Forest, ME. High-precision GPS was used to measure trees across 52 plots and provided robust field data, with ground truth data of tree size and species required for biomass estimation and remote sensing model development. IS2-TEAM and G-TEAM capabilities have been improved, including airborne datasets for ensuring BackPack point clouds are aligned with large scale airborne-captured data. Large-area acquisition systems were initiated for both high-altitude crewed and uncrewed airborne systems. One key advantage of using data-driven AI to generate a canopy height model (CHM) using spaceborne remote sensing data is that the process does not require manual data generation for training. Canopy height from GEDI LiDAR is used to train multi-temporal spaceborne remote sensing data. The model demonstrated higher accuracy when tested in North America vs global CHM models, using USGS 3DEP as a reference. Task 2.2 Broad simulation: Assessment of Maine multi-models continued, with efforts comparing data and assumptions used to estimate stand and landscape conditions and to harmonize the starting point of future projections. ME models are being adapted for IN and GA to expand regional decision-making. Assessment of LANDIS-II in the South began with a four-county test in north FL. Success was achieved in projecting forward the ecological conditions using TreeMap vegetation data and two hypothetical ecoregions. The ME Integrated Forest Sector Model includes habitat suitability for Northeast US biodiversity indicators of interest. Large language model (LLM) systems use satellite imagery and climate data for seamless, goal-oriented urban and peri-urban building and tree planning strategies for desired socio-economic outputs. The system processes a block layout alongside a natural language request and employs LLM computational reasoning and code-generating capabilities. A database of urban block layouts was enriched with socio-economic and weather-related characteristics to enhance contextual understanding. Fall season UAV data as well as leaf tissue samples and spectral data were used to quantify IN stand composition to initiate protocol development and training for functional traits. Preliminary single variable and multivariate models were based on historical data to prepare for the summer campaign in ME. Task 2.4 Data Visualization: Incorporating the PERSEUS Delphi analysis, model and visualization frameworks were co-produced to identify what resonates best with end users, and to develop multiple outputs. Key outputs from the static visualization framework include standing inventory, harvest, carbon storage, habitat conditions and water quality. Key drivers include market demand and land use policy constraints. Natural and urban forests present similar challenges (occlusion, overlaps and lack of resolvability) to segment, locate and analyze trees in extremely dense environments. Satellite (SkySat internationally and UAV NAIP for the US) and UAV data may be used for accurate urban tree crowns to enable species extraction at scale beyond LiDAR. A user-friendly dashboard application is in progress for community foresters, arborists and ecosystem researchers to analyze large datasets. The STAC application generates a leaf-on CHM from leaf-off airborne USGS 3DEP LiDAR data and USGS NAIP aerial images. USGS 3DEP and NAIP collections are not easily findable and accessible though cloud computing platforms, thus a custom daily data ingestion script will harvest information and update the STAC collections. Task 3.1: Stakeholder Perceptions: Results from the Delphi process with forestry professionals was used to inform development of technology and tools to ensure that they align with the needs and interests of the forestry community. These priorities were adopted by PERSEUS Objective 2. Survey instruments were co-developed and implemented, one targeting forest businesses and industries led by UGA and to be adapted for UMaine and Purdue, and the other targeting forest landowners led by Purdue and to be adapted for UGA and UMaine. Both surveys gather quantitative data on individual perceptions, experiences and likelihood of using digital forestry technology. Task 3.2: Scenario development: A systematic review was conducted on forest landowner typologies to inform scenario development. Prior surveys of business owners including baselines done for digital forestry were identified, collected, and reviewed. Survey-based scenario development was employed instead of informal discussions. A scenario development module was added to business and landowner surveys. Task 3.4 Technology Application: Stakeholders were engaged in two single-day UAS & Data Processing workshops; one at the UMaine PERSEUS Year 2 Annual Meeting and a second at Purdue's Digital Forestry Retreat. Both workshops were attended by local/state forestry professionals and as well as our academic members. Objective 4: Education Tasks 4.1 to 4.4 accomplishments are reported in the Training and Professional Development section of REEport.
Publications
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Near-Proximal and Proximal LiDAR for Fine Resolution Forest Inventory at a Scale. Ayman Habib. 2024 USFS Forest Inventory and Analysis Science Symposium (virtual). November 21.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2025
Citation:
Phenotypic data standardization and management. Jinha Jung. Plant and Animal Genome 32 Conference, 1/10/2025, San Diego, CA.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Landscape-level Forest Ecosystem Service Impacts of Uneven-aged Forest Management. A. Daigneault. Society of American Foresters Convention. Loveland, CO. September 17-20 2024.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Landscape-level forest ecosystem service outcomes of uneven-aged forest management. C. Carovillano. IUFRO World Congress, Stockholm, Sweden, June 28, 2024.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Near Proximal and Proximal LiDAR for Fine Resolution Forest Inventory at a Scale. Ayman Habib. 2024 Forest Inventory and Analysis Science Symposium, November 21.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Near Proximal and Proximal Sensing for a Sustainable Environment: Opportunities and Challenges in Forest Inventory. Ayman Habib. Annual Conference of the Egyptian-American Scholars (AEAS-S51), Cairo, Egypt, December 24.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Near Proximal and Proximal Sensing for a Sustainable Environment: Opportunities and Challenges in Forest Inventory and Smart Agriculture. Ayman Habib. GRASP Laboratory, School of Engineering and Applied Science, University of Pennsylvania, December 13.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Near Proximal and Proximal Sensing for a Sustainable Environment: Opportunities and Challenges in Forest Inventory. Ayman Habib. Keynote at the 2024 K-Geo Festa Digital Earth: Better life for all, November 6.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Near Proximal and Proximal Sensing for Fine Scale Forest Inventory. ASPRS Mid-South Regional Conference: Mapping, Monitoring, and Modeling for Climate Security, Oak Ridge National Laboratory, May 10th, 2024, Ayman Habib.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Proximal, Near-Proximal, and Airborne LiDAR for Fine Resolution Forest Inventory at a Scale. Ayman Habib. Institute of Digital Forestry Annual Meeting, August 1.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Remote Sensing of MEs Forests, teachers workshop, Challenger Center, Bangor, ME, Daniel Hayes
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Smartphone Circular Plot Forest Inventory. Victor Chen. 2024 USFS Forest Inventory and Analysis Science Symposium (virtual).
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Species identification with canopy images and deep learning techniques. Yunmei Huang, Botong Ou, Kexin Meng, Baijian Yang, Joshua Carpenter, Jinha Jung, Songlin Fei. Ecological Society of America, August 7. Long Beach, California.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Sustainability of forest industries and their linkages with ecosystem services. Tiwari, M., Siry, J., & Abrams, J. PERSEUS Annual Meeting, Orono, Maine.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
The ecological role of structural diversity. S Fei. American Geophysical Union. Washington, DC. Dec. 2024. (invited)
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Tree species identification from point clouds by fine-tuning CLIP. Jinyuan Shao, Songlin Fei. American Geophysical Union.
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2025
Citation:
Ou, B., Shao, G., Yang, B., Fei, S. 2025. FocalSR: Revisiting image super-resolution transformers with fourier-transform cross attention layers for remote sensing image enhancement, Geomatica, 77, 1, 100042, DOI: 10.1016/j.geomat.2024.100042
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2024
Citation:
Foster, A.E., Rahimzadeh-Bajgiran, P., Daigneault, A., Weiskittel, A. 2024. Cost-effectiveness of remote sensing technology for spruce budworm monitoring in Maine, USA. Forests Monitor 1(1):66-98. DOI: 10.62320/fm.v1.i1.14.
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2024
Citation:
Goel, A., Song, H., Jung, J. 2025. Integrating Sparse LiDAR and Multisensor Time-Series Imagery From Spaceborne Platforms for Deriving Localized Canopy Height Model. in IEEE Transactions on Geoscience and Remote Sensing, vol. 63, pp. 1-13, 2025, Art no. 4404913, DOI: 10.1109/TGRS.2025.3542685.
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2024
Citation:
Chivhenge, E., Ray, D.G., Weiskittel, A.R., Woodall, C., D'Amato, A. 2024. Evaluating the Development and Application of Stand Density Index for the Management of Complex and Adaptive Forests. Current Forestry Reports. 10: 10, 133152. DOI: 10.1007/s40725-024-00212-w.
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2025
Citation:
dos Santos, R.C., Shin, S-Y., Manish, R., Zhou, T., Fei, S., Habib, A. 2025. General Approach for Forest Woody Debris Detection in Multi-Platform LiDAR Data. Remote Sensing. 2025; 17(4):651. DOI: 10.3390/rs17040651.
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2024
Citation:
Huang, Y., Ou, B., Meng, K., Yang, B., Carpenter, J., Jung, J., Fei, S. 2024. Tree Species Classification from UAV Canopy Images with Deep Learning Models. Remote Sensing, 16(20), 3836. DOI:10.3390/rs16203836.
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2025
Citation:
Huang, Y., Yang, B., Carpenter, J., Jung, J., Fei, S. 2025. Temperate forest tree species classification with winter UAV images, Remote Sensing Applications: Society and Environment, 37, 101422. DOI: 10.1016/j.rsase.2024.101422.
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2024
Citation:
Jain, A., Benes, B., Cordonnier, G. 2024. Efficient Debris-flow Simulation for Steep Terrain Erosion, Association for Computing Machinery, New York, NY, USA, 43:4. DOI: 10.1145/3658213.
- Type:
Book Chapters
Status:
Published
Year Published:
2024
Citation:
Jung, J., Fei, S., Tuinstra, M., Yang, Y., Wang, D., Song, C., Gillan, J. et al. 2024. Data to Science: An Open-Source Online Platform for Managing, Visualizing, and Publishing UAS Data. In Autonomous Air and Ground Sensing Systems for Agricultural Optimization and Phenotyping IX, edited by Christoph Bauer and J. Alex Thomasson, 13053:1215. SPIE.
- Type:
Books
Status:
Published
Year Published:
2025
Citation:
Lee, J.J., Li, B., Beery, S., Huang, J., Fei, S., Yeh, R., Benes, B. 2025. Tree-D Fusion: Simulation-Ready Tree Dataset from Single Images with Diffusion Priors. In: Leonardis, A, Ricci, E, Roth, S, Russakovsky, O, Sattler, T, Varol, G. (eds) Computer Vision ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15099. Springer, Cham. DOI: 10.1007/978-3-031-72940-9.
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2024
Citation:
Lee, T., Vatandaslar, C., Merry, K., Bettinger, P., Peduzzi, A., Stober, J. 2024. Estimating Forest Inventory Information for the Talladega National Forest Using Airborne Laser Scanning Systems. Remote Sensing, 16(16), 2933. DOI: 10.3390/rs16162933.
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2024
Citation:
Li, B., Schwarz, N.A., Pa?ubicki, W., Pirk, S., Benes, B. 2024. Interactive Invigoration: Volumetric Modeling of Trees with Strands, Association for Computing Machinery New York, NY, USA, 43:4, DOI: 10.1145/3658206
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2024
Citation:
Roy, S., Wei, X., Weiskittel, A., Hayes, D.J., Nelson, P., Contosta, A. 2024. Influence of climate zone shifts on forest ecosystems in northeastern United States and maritime Canada. Ecological Indicators 160 (2024): 111921. DOI: 10.1016/j.ecolind.2024.111921.
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2024
Citation:
Shao, J., Lin, Y-C., Wingren, C., Shin, S-Y., Fei, W., Carpenter, J., Habib, A., Fei, S. 2024. Large-scale inventory in natural forests with mobile LiDAR point clouds, Science of Remote Sensing, Volume 10, 2024, 100168, ISSN 2666-0172, DOI: 10.1016/j.srs.2024.100168.
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2024
Citation:
Vatandaslar, C., Lee, T., Bettinger, P., Ucar, Z., Stober, J., Peduzzi, A. 2024. Mapping percent canopy cover using individual tree- and area-based procedures that are based on airborne LiDAR data: Case study from an oak-hickory-pine forest in the USA. Ecological Indicators. 167: Article 112710. DOI: 10.1016/j.ecolind.2024.112710.
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2024
Citation:
Wang, J., Choi, D.H., LaRue, E., Atkins, J.W., Foster, J.R., Matthes, J.H., Fahey, R.T., Fei, S., Hardiman, B.S. 2024. NEON-SD: A 30-m Structural Diversity Product Derived from the NEON Discrete-Return LiDAR Point Cloud. Scientific Data, 11(1), 1174. DOI: 10.1038/s41597-024-04018-0.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2025
Citation:
Advances in digital forestry challenges and opportunities. S Fei. University of Idaho. Mar. 2025. (invited)
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Airborne LiDAR for Fine Resolution Forest Inventory at a Scale: Investigation of Linear, Geiger, and Single Photon LiDAR. Ayman Habib. EFFICACI/TNC/Purdue Partner Meeting, October 4.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Are remote sensing-backed forest inventory models and maps reliable for large and structurally-complex forests? Vatandaslar, C., T. Lee, P. Bettinger, J. Stober. 14th North American Forest Ecology Workshop, Asheville, NC. June 27, 2024
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Building an Open Geospatial Data Ecosystem, Ideation Workshop: 3D Mapping of the Amazon. Jinha Jung. 12/9-10/2024, Princeton, NJ.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2025
Citation:
Data to Science: Modular open-source ecosystem for high throughput phenotyping. Jinha Jung. Plant and Animal Genome 32 Conference, 1/11/2025, San Diego, CA.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Deep learning-based method for tree trunk detection and species recognition. Yunmei Huang, Charles Warner, Rado Gazo, Songlin Fei. American Geophysical Union, Fall Meeting, Dec 13, 2024, Washington, D.C.
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2024
Citation:
Warner, C., Wu, F., Gazo, R., Benes, B., Kong, N., Fei, S. 2024. CentralBark Image Dataset and Tree Species Classification Using Deep Learning. Algorithms, 17(5), 179. DOI: 10.3390/a17050179.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Zhao, H., Huang, H., Zhang, T., Yang, B., Wei-Kocsis, J., Fei, S. 2024. Unsupervised Machine Learning for Detecting and Locating Human-Made Objects in 3D Point Cloud. IEEE International Conference on Big Data (BigData), Washington, DC, USA, pp. 1500-1507. DOI: 10.1109/BigData62323.2024.10825112.
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2024
Citation:
Zhou, T., Zhao, C., Wingren, C.P., Fei, S., and Habib, A. 2024. Forest feature LiDAR SLAM (F2-LSLAM) for backpack systems. ISPRS Journal of Photogrammetry and Remote Sensing, Volume 212, 2024, Pages 96-121, ISSN 0924-2716, DOI: 10.1016/j.isprsjprs.2024.04.025.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Estimating canopy cover of natural forests using airborne laser scanning (ALS) data: A case from Alabama, USA. Vatandaslar, C., T. Lee, A. Peduzzi, P. Bettinger, K. Merry, and J. Stober. IUFRO World Congress, Stockholm, Sweden, June 28, 2024.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Demonstrating a Carbon MMRV Prototype for MEs Working Forests: Results from a Stakeholder-driven, Landscape Model-data Framework. Hayes, D. J., Wei, X., Simons-Legaard, E., Legaard, K., Weiskittel, A., Cook, B., & Woodall, C. Annual Meeting of the American Geophysical Union, Washington DC.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Digital Forestry. S. Fei. The Southern Group of State Foresters Annual Meeting. Wilmington, NC. June 2024. Keynote speaker
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Discovering the Unseen: Modular open-source ecosystem for geospatial data science. Jinha Jung. Institute for Plant Sciences Remote Sensing Workshop, 12/13/2024, West Lafayette, IN.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Generative AI for Urban Structures and Forests. Adnan Firoze, Daniel Aliaga. 2024 USFS Forest Inventory and Analysis Science Symposium (virtual) November 21.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
Global Economic, Timber, and Carbon Implications of Alternative Forest Plantation Growth Pathways. A. Daigneault. IUFRO World Congress, Stockholm, Sweden, June 28, 2024.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
GNSS through the trees: Smartphone capabilities under forested conditions. Merry, K., P. Bettinger. IUFRO World Congress, Stockholm, Sweden. June 25, 2024.
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2024
Citation:
High Resolution Soil Moisture and Biomass Sensing Using S-Band Synthetic Aperture Radar on a UAV Platform. W. Li, M. Crawford, L. Azimi, M. Inggs, J. Garrison. American Geophysical Union, Fall Meeting, Dec 13, 2024, Washington, D.C.
|
Progress 04/01/23 to 03/31/24
Outputs
Target Audience:The target audience in this establishment year has been our internal multi-disciplinary team. Our communications have focused on increasing the familiarity among our wide range of scientists, engineers and trainees, development of the project-wide implementation plan and facilitating points of integration among Objectives. External Advisory Board members, professional staff, postdoctorals and graduate and undergraduate students have been recruited into the project. Task 1.3 has begun engagement with forestry stakeholder professionals in a Delphi-method survey to help inform forest management decisions including planning, accounting and forecasting potential issues. Changes/Problems:
Nothing Reported
What opportunities for training and professional development has the project provided?Purdue's Institute for Digital Forestry encompasses over 50 graduate students and postdoctoral researchers. Though many are working on research directly related to PERSEUS, 4 grads and 3 undergrads are presently supported, or partially supported, by PERSEUS funding. Maine supports 5 grads/postdocs. The UGA team includes 3 non-thesis MS students supported through the UGA Center for Forest Business, and 6 graduate students (PhD and MS) supported through PERSEUS. A questionnaire on professional development activities was deployed to PERSESUS students and postdocs and the broader Purdue Digital Forestry student list in January 2023. This survey assessed topics and delivery methods students were most interested in for professional development activities. Two virtual professional development workshops were presented to PERSEUS graduate and undergrad students, bringing together students across the three institutions. The first, focused on science communication, had 9 student participants total (of which 2 were PERSEUS students). A learning module "Managing your online research presence," was developed to train PERSEUS students with online tools like Google Scholar profiles and ORCiD to track/manage their research-related activities. The module was offered in Spring 2024. It had 7 students, all PERSEUS. Plans are to increase the frequency of these workshops to approximately monthly. Undergrad students were on-boarded at UGA to assist with Objective 1 activities (LiDAR data processing and wood bark image collection) and Objective 4 (OLAF AI course development). Three non-thesis MS students (not funded by PERSEUS) are assisting in the development of south-wide GIS databases (roads, streams, soils, ownership, etc.). How have the results been disseminated to communities of interest?Preliminary progress updates have been shared only internally within the PERSEUS institutions in this establishment year. Early scientific accomplishments have been published through five refereed publications in our academic fields and 9 other presentations or events. What do you plan to do during the next reporting period to accomplish the goals?Task 1.1 iForester: We will improve algorithm robustness for DBH measurement and species identification with regional specificity, and further develop biometrics measures such as stem straightness and volume. We will combine smartphone LiDAR and RGB sensors to achieve automated measurement with high accuracy (Deliverable #1). The team also will use Real Time Kinematics (RTK) extensions of the smartphone, which are enabled by communication with permanently operating GNSS reference stations, to achieve 1 cm positional accuracy. Using such extensions is expected to improve the developed algorithm performance. These somewhat less expensive units may be evaluated for student laboratory coursework (Objective 4). Task 1.2: StemMapper: We will address multiple ongoing data analytics challenges: a) Tree-scale measurement, b) Species identification and c) Stand to landscape-scale inventories (Deliverable #3). We will continue improvement of the Backpack Mobile Mapping hardware and software systems for the integration of multi-beam spinning LiDAR, solid-state LiDAR, consumer-grade cameras, machine vision cameras and GNSS/INS units (Deliverable #2). An improved hardware design of the Backpack will facilitate a scalable system for implementation by stakeholders. The performance of F2-SLAM and S2-TEAM strategies will be enhanced to ensure the Backpack LiDAR systems' reliability against extended GNSS-signal occlusions in dense canopy under leaf-on conditions. More specifically, the ability to include tree detection, localization, and segmentation in the trajectory enhancement and point cloud generation will be expanded. Field data acquisition guidelines for track/flight configuration will be developed to allow for optimal mission planning strategies, sufficient data acquisition to ensure the geometric fidelity of derived products and successful integration of acquired data. Work will be done on data acquisition guidelines that relates to pros and cons of LiDAR, multi-spectral, and RGB. We will advance the multi-system integration of both UAV and Backpack datasets in a single System Calibration and Trajectory Refinement Procedure to take advantage of the near-proximal and proximal sensing nature of these systems. Task 1.3: Data Coverage: We will initiate a comparison analysis of a suite of existing and newly developed data products for regional-scale forest carbon assessment (Deliverable #4). Starting as a pilot project focusing on Maine with plans to expand to other states and regions of the eastern U.S., we will analyze data products including both maps of forest biomass and forest carbon model outputs. The forest biomass maps include estimations based on modeling airborne (e.g., USGS 3DEP, USDA 3D NAIP, and NASA G-LiHT) and spaceborne LiDAR (e.g., NASA GEDI), as well as air photo (i.e., NAIP) point clouds, evaluated against ground-based inventory (i.e., from the US Forest Inventory and Analysis (FIA) program) plot summaries. For forest carbon model outputs, we are comparing baseline (historical) estimates and future projections of different climate and management scenarios at various spatial scales. These models include the Forest Vegetation Simulator (FVS), LANDIS-II, the Canadian Carbon Budget Model (CBM-CFS3), and the Community Land Model (CLM) as evaluated against growth and yield data derived from FIA. Tasks 2.1 Landowner optimization and 2.2 Broad simulation: We will combine geospatial and spectral (Purdue LeafSpec scanner) resolutions to develop revolutionary imaging processing algorithms for more accurate and earlier detection of disease and stress trends to optimize ecosystem services at the local level and then scale to stand and landscape level assessments. This effort will collect paired spectral and leaf reference (i.e., chemistry and physiology) measurements that can serve as input variables for scaling information to air and space borne platforms. The Maine multi-model (FVS, LANDIS-II, CBM) will be adapted for Purdue and UGA for intercomparison and initiating regional decision-making frameworks. The Broad-scale scenario development effort (feeding 2.3 Value Chain [Year 3] and 2.4 Visualization) will analyze tree changes over time at large scale and relate to tree and forest health and disease trends. Task 2.4 Data Visualization: We will focus on broadening the regional coverage and diversifying the data collection efforts while maintaining the geospatial data layers hosted on the STAC service and D2S. Task 3.1: Stakeholder Perceptions: We will complete the Delphi process with forestry professionals. Results of the process will be used to further inform the development of technology and tools to ensure that they align with the needs and interests of the forestry community. Two survey instruments will be developed in Year 2, one led by Georgia and to be adapted for Maine and Indiana targeting forest businesses and industries, and the other led by Purdue and to be adapted by Georgia and Maine targeting forest landowners. Both surveys will be designed to gather quantitative data on individual perceptions, experiences and likelihood to use digital forestry technology. Task 3.2: Scenario development: We will assess management approaches based on landowner typology and evaluate "Future Visions" for the forest sector (e.g., ASU, For/Me). A pilot survey instrument in at least one state will be developed to evaluate risk perceptions and state preference elicitation techniques. Landowner typologies will be determined by linking ownership, regional socio-economic and FIA plot data to estimate forest management and harvest decisions over the past 20 years. Task 3.4 Technology Application: We will test digital technology and assess facilitators and barriers to adoption through a series of workshops, training sessions and other venues. Task 4.1 Learning communities: The undergraduate VIP cohort will be mentored in a course-based research experience. Task 4.2 Interns and fellows: Undergraduate research cohortswill continue to be recruited in VIP and non-VIP research activities. Professional development programs for graduate students will be further refined and implemented. Graduate students will be trained in mentorship skills and serve as mentors for the undergraduate cohorts. Task 4.3 Curriculum development: An initial hands-on field technology workshop will occur at the Summer annual meeting. This will encompass forest data acquisition employing UAVs and subsequent data processing and analysis and will include PERSEUS students and potentially area stakeholders. Task 4.4 Online certificate: The UAV Forest Data Acquisition and Processing workshop will be refined for inclusion in Purdue online Master of Forestry in Digital Natural Resources degree program.
Impacts
What was accomplished under these goals?
Task 1.1 iForester: Algorithms for the iPhone app were developed to automatically calculate DBH (with sub-inch accuracy) on individual trees given minimal user input. The prototype will advance transfer learning on region-specific bark images to retrain our lightweight Distilled-MoblieNet-V2 AI model to ensure tree identification accuracy for regions of the eastern forest. UGA interns are collecting images of tree bark for the SE. Task 1.2 StemMapper: Our custom-designed LiDAR-based and AI-assisted StemMapper platforms for automated stem- and stand-level inventory includes 4 Backpack and 2 UAV systems with integrated Global Navigation Satellite System/Inertial Navigation System (GNSS/INS), multi-beam spinning LiDAR and digital camera. The systems have been repeatedly tested through a data acquisition process that includes: 1) gathering of GNSS/INS, image and LiDAR data using proximal (Backpack and smartphone) and near-proximal (UAV) systems; 2) processing of GNSS/INS data for generation of geo-tagged imagery and point clouds; 3) data correctness and completeness quality control; 4) solicitation of airborne sensing data, e.g., Geiger-mode and 3D Elevation Program (3DEP) LiDAR, to evaluate the added benefit of proximal and near proximal sensing systems; and 5) in-field acquisition of reference data. The systems have undergone rigorous system calibration to precisely estimate the spatial and rotational offsets. Datasets have been collected from plots with extensive ground truth data for hardware integration verification: 3 plots in Purdue Martell Forest, 4 at the ME Penobscot Experimental Forest and 11 in the AL Talladega National Forest. Task 1.3: Data coverage: The main challenge in data coverage is ensuring the fidelity of collected geospatial data by integrated hardware (UAV and Backpack) and other geospatial data acquisition systems (e.g., Linear/Geiger-mode LiDAR systems on crewed aircraft). LiDAR-based Trajectory Enhancement and Mapping (TEAM) functionalities were developed to improve Backpack trajectory, which is compromised by GNSS-signal occlusions by tree canopies. Forest Feature Simultaneous Localization and Mapping (F2- SLAM) and Integrated Scan Simultaneous Trajectory Enhancement and Mapping (S2- TEAM) strategies were developed to improve Backpack data quality. This allows for integration of UAV/airborne LiDAR data, existing Digital Terrain Model and publicly available point cloud data (e.g., 3DEP) to improve the georeferencing quality of Backpack LiDAR data and ensure seamless transition between proximal, near proximal and remote aircraft data. Tasks 2.1-2.3: Leaf-scale measurement modeling and multi-model (FVS, LANDIS-II, CBM) intercomparison activities were initiated using Maine data as a pilot case. We developed an initial catalog of broad-scale simulation scenarios and also a framework for stakeholder-driven scenario development. Task 2.4 Data Visualization: A Spatio-Temporal Asset Catalog (STAC) was created and deployed at https://stac.digitalforestry.org to collect, organize and host LiDAR, imagery and GIS datasets with Purdue/IN geospatial data and geospatial data from UME and UGA. Purdue hosts UAV datasets using the Data to Science (D2S) platform (https://perseus.d2s.org) specifically designed for uploading, processing, visualizing and sharing UAV data using cloud optimized formats. In support of modeling efforts, broad-scale southern GIS databases (streams, roads, soils and some landowner parcels) are being acquired, developed and cataloged. Approximately 44TB of initial datasets have been, or are being, collected for ingestion. Task 3.1: Stakeholder Perceptions: To identify stakeholder needs, we initiated a compilation of prior surveys of forest business owners, forestry professionals and landowners on digital forestry topics. We outlined sampling frames for state-level data collection specifically concerning technology use and landowner typologies. We adopted the Delphi method for the purpose of generating in-depth insights and establishing a consensus opinion by prioritizing technology needs of forestry professionals in the Eastern U.S. Delphi involves rounds of data collection and analysis that bring together "a panel of experts, having them complete a series of questionnaires individually, and sharing these anonymized answers within the panel to allow for feedback and debate. The experts are presented with aggregated summaries of responses after each round, allowing each expert to adjust their assessment of priorities according to the group perspectives". Preliminary Round 1 analyses revealed the need for data and tools that would help inform forest management decisions including planning, accounting, and forecasting potential issues. Key factors that could influence the adoption of digital technologies include usability, accuracy, cost, organizational capacity, complexity, comparative advantage and access to the tools. Task 3.2: Scenario development: Prior work in ME, GA and IN was related to forest products and ecosystem services scenario development. We assessed the UME model and what-if scenario framework (previously developed and published) for adaptation to GA and IN. Informal discussions have begun with stakeholders (IHA, CFRU, lumber associations) to host regional or cross-regional workshops for input on scenario development. Task 4.1 Learning communities: We assessed the Learning Community infrastructure at each institution to explore the feasibility of a university-level PERSEUS-designated community. A determination was made to focus on a cross-partner hybrid Learning Community consisting of an undergraduate student cohort experience and a graduate student / postdoc professional development community. PERSEUS is leveraging existing UGA and Purdue Vertically Integrated Projects (VIP) and Purdue DataMine learning communities and internship projects. The first round will begin in Summer 2024; adopting and following best practices from other successful undergraduate student programs (e.g., NSF REU). Task 4.2 Interns and fellows: An undergraduate student experience is under development that will encompass a cohort experiential learning framework. Five undergraduate students have been supported at UGA and Purdue. Task 4.3 Curriculum development: "Enhanced Forest Inventory and Analysis" introduced 7 UME students in forestry and natural resources to the era of Big Data and its applications, with a particular focus on the scaling linkages, via state-of-the-art modeling approaches, between the detailed measurements collected in the field and proximal remote sensing to broader scale mapping tools using remote sensing technologies (airborne LiDAR and satellite multispectral imaging). The hybrid course is intended for traditional graduate students and postgraduates from the professional workforce. Purdue is developing an online Master of Forestry in Digital Natural Resources degree that will target working professionals to add skillsets focused on data acquisition, analysis and application using next-generation approaches including UAVs, environmental sensor networks, LiDAR remote sensing, multispectral imaging and photogrammetry. Industry and agency stakeholders indicate broad support and ample demand for this program. The proposal was submitted for evaluation and approval by the Purdue administration in Spring 2024. Elements of this program will be tested during the 2024 PERSEUS annual meeting through workshops providing instruction and hands-on experience to PERSEUS students, postdoctoral researchers and area stakeholders. Task 4.4 Online certificate: OLAF (Online Learning in Applied Forestry) courses on remote sensing and artificial intelligence are being developed by forestry and AI collaborators at UGA. Purdue and UME colleagues will provide feedback. Continuing education credits will be certified by the Society of American Foresters.
Publications
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Li, B., Klein, J., Michels, D. L., Pirk, S., Benes, B., Palubicki, W. (2023). Rhizomorph: The Coordinated Function of Shoots and Roots. ACM Transaction on Graphics, 42(4). DOI: 10.1145/3592145
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Roy, S., Wei, X., Weiskittel, A., Hayes, D.J., Nelson, P., Contosta, A. 2024. Influence of climate zone shifts on forest ecosystems in northeastern United States and maritime Canada. Ecological Indicators 160: 111921. DOI: 10.1016/j.ecolind.2024.111921
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Shao, Jinyuan & Habib, Ayman, Fei, S. (2023). Semantic Segmentation of UAV Lidar Data for Tree Plantations. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. XLVIII-1/W2-2023. 1901-1906. 10.5194/isprs-archives-XLVIII-1-W2-2023-1901-2023. DOI:10.5194/isprs-archives-XLVIII-1-W2-2023-1901-2023.
- Type:
Websites
Status:
Published
Year Published:
2023
Citation:
PERSEUS web: https://ag.purdue.edu/digital-forestry/projects/perseus/index.html
- Type:
Websites
Status:
Published
Year Published:
2023
Citation:
Spatio-Temporal Asset Catalog (STAC): https://stac.digitalforestry.org
- Type:
Journal Articles
Status:
Published
Year Published:
2023
Citation:
Cordonnier, G., Jouvet, G., Peytavie, A., Braun, J., Cani, M.-P., Benes, B., Galin, E., Gu�rin, E., Gain, J. (2023). Forming Terrains by Glacial Erosion. ACM Transaction on Graphics, 42(4). DOI: 10.1145/3592422
- Type:
Journal Articles
Status:
Published
Year Published:
2024
Citation:
Lee, Jae Joong, Li, Bosheng, Benes, Bedrich. (2024) Latent L-systems: Transformer-based Tree Generator. ACM Transactions on Graphics. 43(102): pp 116. DOI: 10.1145/3627101.
|