Forests provide critical ecosystem services, such as climate moderation, erosion control, freshwater protection, and pollutant amelioration and sequestration. Forests represent our nation’s largest terrestrial carbon sink, contributing an equivalent of 81% of the nation’s net carbon uptake. However, long-term forest sustainability is threatened due to intensified environmental challenges (e.g., droughts, pest outbreaks), evolving markets (e.g., carbon and pulp), and land use changes. This is particularly true for the more densely populated Eastern U.S.

Dynamic, data-driven tools for the forest industry are required to effectively adapt to increasingly complex economic and climate conditions. Additionally, the forestry workforce struggles with an education gap between traditional logistical and operational skills and the surge of digital and computational data as technologies become increasingly affordable and available. Integrated tools, which inform and engage stakeholders, and a digitally competent workforce are essential to strengthen the resilience of the Eastern U.S. forest region.

This project will pioneer and integrate digital advances to revolutionize forestry with high-efficiency measurement tools and data-driven policy and decision-making. An integrated decision-support system, powered by wall-to-wall high-resolution information produced by PERSEUS, will provide a “digital bridge” between strategic national/regional-level policy and local-level tactical decision-making and climate-smart forest management practices. Coupled with Extension, outreach, and education efforts, as well as engaging stakeholders across the value chain, PERSEUS will ultimately facilitate a diverse and digitally competent workforce focused on data-driven management decisions that optimize operations and policies to assure the adaptation, mitigation, and resilience of forestry production systems to climate change.

PERSEUS (Promoting Economic Resilience and Sustainability of the Eastern U.S. forests) will provide scientifically-sound information, outreach, and educational opportunities that lay the foundation for a paradigm shift in forestry toward data-driven, artificial intelligence (AI)-supported forest management systems that increase both the provision of ecosystem services and operational efficiency under the uncertainty of climate change. PERSEUS will develop measurement and monitoring tools, data-driven decision systems, and management practices through a unified effort of automated measurement, integrated multi-objective modeling, engaged climate-smart management, and a digitally competent mindset in students and professionals.

• Objective 1 Measurement Automation: 
  • Develop scalable automated data capture systems with integration of multimodal,
    multiplatform and multitemporal data to assist stakeholder data-driven forest management practices and decisionmaking.
• Objective 2 Model Integration and Application:
  
  • Create a multimodel ensemble that is locally calibrated and capable of projecting forest ecosystem services under a range of conditions.
• Objective 3 Informed and Engaged Mindset:
  • Encompass stakeholder actions, motivations and values to inform the development and implementation of optimized climate-smart management systems that increase the capacity of forest production and ecosystem services.
• Objective 4 Digitally Competent Mindset:
  • Contribute to measurable national impacts through the development of educational programs for digitally-competent and capable practitioners, managers and researchers who can pipeline into successful academic, industry or governmental careers.

TRAINING AND PROFESSIONAL DEVELOPMENT

• A learning module “Managing your online research presence,” was developed to train PERSEUS students with online tools like Google Scholar profiles and Open Researcher and Contributor Identifier (ORCiD) to track/manage their research-related activities. The module was offered in Spring 2024.
• A questionnaire on professional development activities was deployed to PERSEUS students and postdoctoral researchers and the broader Purdue’s Institute for Digital Forestry student list in January 2023. This questionnaire assessed topics and delivery methods students were most interested in for professional development activities. Two virtual professional development workshops were presented by UMaine to PERSEUS graduate and undergraduate students, bringing together students across the three institutions. The first focused on science communication and had nine student participants total (of which two were PERSEUS students). The second was a short session on “Managing your online research presence” that had seven students, all PERSEUS. Plans are to increase the frequency of such workshops to approximately monthly.
• Purdue’s Institute for Digital Forestry encompasses over 50 graduate students and postdoctoral researchers. Though many are working on research directly related to PERSEUS, two are presently supported by PERSEUS funding. UMaine supports five graduate students. The UGA team includes three non-thesis Master’s (MS) Degree students supported through the UGA Center for Forest Business, and six graduate students (MS and Doctor of Philosophy [PhD]) supported through PERSEUS.
• Interns were on-boarded at UGA to assist with Objective 1 activities (Light Detection and Ranging [LiDAR] data processing and wood bark image collection) and Objective 4 (Online Learning in Applied Forestry [ OLAF] AI course development). Two non-thesis MS students (not funded by PERSEUS) are assisting in the development of south-wide Geographic Information System (GIS) databases (roads, streams, soils, ownership, etc.).

AUTOMATED (RESEARCH)

Develop, evaluate, and integrate sensors, multi-stream data, and AI algorithms to create a set of digital tools and wall-to-wall coverage data that will provide refined, near real-time, and spatially-explicit measurements. We will develop novel data acquisition systems and data analytics to better measure and monitor timber and fiber production, greenhouse gas (GHG) mitigation (carbon sequestration, wildfire fuel assessment), and other ecosystem services for every acre across the Eastern U.S.

Task 1.1 iForester (mo. 1-36): Develop an integrated AI-assisted iForester (measurement tool—ground truth/inventory measurements) smartphone app that automatically inventories major tree species for the Eastern forest with two key functions: 1) AI-assisted species recognition using tree bark and 2) LiDAR-Red Green Blue (RGB) image enabled measurements of key tree biometric measures.

Task 1.2 StemMapper (mo. 1-36): Create a LiDAR-based and AI-assisted StemMapper (proximal and near proximal remote sensing-derived models and products) to provide stem-level inventory at the stand and tract level with large scale automated inventory for multi-objective climate-smart management for forestry professionals.

Task 1.3 Data Coverage (mo. 1-54): Generate multi-scale data products (fiber, habitat, carbon, etc.) with higher spatial and temporal resolution for every acre across the Eastern U.S. to facilitate both local and regional level management optimization.

Deliverables Year 1

• Smartphone App
  • Initial
• Hardware Integration
  • Initial
• Data Analytics
  • Initial

Accomplishments in Year 1

Task 1.1 iForester: We have developed algorithms for a smartphone app (iPhone initially) to automatically calculate Diameter at Breast Height (DBH) (Deliverable #1) on individual trees given minimal user input such as tapping the photo image of tree base on the screen. Our app achieved sub-inch DBH measurement accuracy. The prototype will soon be released for evaluation and data collection among a group of selected users. The app will advance transfer learning on region-specific bark images to retrain our AI model (a lightweight Distilled-MoblieNet-V2) to ensure tree identification accuracy for regions of the Eastern forest. UGA interns are collecting images of tree bark for the southeast. A companion app (iPhone and Android) is based on a circular plot survey using machine learning tree segmentation demonstrated the feasibility but with low accuracy.

Task 1.2 StemMapper: Custom-designed equipment for the LiDAR-based and AI-assisted StemMapper for automated stem- and stand-level inventory has been assembled including four BackPack and two uncrewed aerial vehicle (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 near-proximal (UAV) and proximal (BackPack and smartphone) sensing systems; 2) preliminary processing of GNSS/INS data for the generation of geo-tagged imagery and point clouds; 3) preliminary quality control for checking data correctness and completeness; 4) solicitation of airborne sensing data (e.g., Geiger-mode and 3D Elevation Program [3DEP] LiDAR), to evaluate the added benefit of near proximal and proximal sensing systems; and 5) in-field acquisition of reference data (e.g., manual DBH measurements). The systems have undergone rigorous system calibration to precisely estimate the spatial and rotational offsets among the LiDAR, digital camera, and GNSS/INS units. To verify the hardware integration, several datasets have been collected from three plots in Martell Forest (IN), four plots at the Penobscot Experimental Forest (ME), and 11 plots in the Talladega National Forest (AL). These plots have extensive ground truth data for verification.

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., acquired LiDAR data by Linear/Geiger-mode LiDAR systems onboard crewed aircrafts). In this regard, LiDAR-based Trajectory Enhancement and Mapping (TEAM) functionalities have been developed for improving the BackPack trajectory, which is compromised by GNSS-signal occlusions by tree canopy. Forest Feature Simultaneous Localization and Mapping (F₂-SLAM) and Integrated Scan Simultaneous TEAM (IS₂-TEAM) strategies have been developed to improve the quality of the BackPack data. These strategies allow for the integration of UAV/airborne LiDAR data, existing Digital Terrain Model (DTM), and publicly-available point cloud (e.g., 3DEP data) to improve the georeferencing quality of the BackPack LiDAR data and ensure seamless transition from proximal (BackPack), near proximal (UAV), to remote (crewed aircraft) LiDAR data. We have acquired Geiger-Mode LiDAR data, Single Photon LiDAR data, and Linear LiDAR data to evaluate the level of detail in multi-resolution datasets as well as evaluate the success of the F₂-SLAM and IS₂-TEAM strategies.

Plans for the Coming Year, April 2024-March 2025

Deliverables Year 2

• Smartphone App
• Hardware Integration
• Data Analytics
• Data Fusion

Task 1.1 iForester: We will improve algorithm robustness for DBH measurement and species identification with regional specificity, and further develop biometric 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 will also 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 IS₂-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 in UMaine 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., U.S. Geological Survey [USGS] 3DEP, U.S. Department of Agriculture [USDA] 3D National Agriculture Imagery Program [NAIP], and National Aeronautics and Space Administration [NASA] Goddard’s LiDAR, Hyperspectral, and Thermal Imager [G-LiHT]) and spaceborne LiDAR (e.g., NASA Global Ecosystem Dynamics Investigation [GEDI]) LiDAR, as well as air photo (i.e., NAIP) point clouds, evaluated against ground-based inventory (i.e., from the U.S. 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.

Integrated Multi-Objective (Research)

Leverage Objective 1 to construct and apply an integrated framework for modeling current and future forest ecosystem service trends under climate change for multi-objective optimization at the landowner scale, while providing multi-stakeholder simulations and tradeoff analyses of forest management at the regional scale. Develop a generalized simulation/optimization framework to inform regionally appropriate climate adaptation and resilience solutions.

Task 2.1 Landowner Optimization (mo. 13-48): Link available forest data (from PERSEUS and existing datasets such as FIA) to our integrated multi-model ensemble to optimize ecosystem services at a local scale (1–1,000,000 ha).

Task 2.2 Broad Simulation (mo. 13-48): Co-develop (with stakeholders) a dynamic simulation system to present broad-scale (>1M ha) assessments of alternative policy and market scenarios, while facilitating fine-scale assessments of trade-offs among management and ecosystem services for regional decision-making.

Task 2.3 Value Chain (mo. 25-60): Develop and refine methods to investigate potential efficiencies through forest management activities in the Eastern U.S.

Task 2.4 Data Visualization (mo. 1-60): Develop a cloud-based data warehouse to allow key project data to be stored, visualized, and shared with stakeholders.

Deliverables Year 1

• Geospatial Information System

Accomplishments in Year 1

Tasks 2.1–2.3: The identification of leaf-scale measurement modeling activities were initiated as well as the multi-model (FVS, LANDIS-II, CBM) intercomparison using UMaine data as a pilot case. We developed an initial catalog of background material for broad-scale simulation scenarios, and developed 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 all available LiDAR, imagery, and GIS datasets from UMaine, UGA, and Purdue. The STAC service presently includes Purdue/Indiana geospatial data, with additional geospatial data from UMaine and UGA being added. Purdue hosts UAV datasets using the Data to Science (D2S) platform (https://perseus.d2s.org), which is specifically designed for uploading, processing, visualizing, and sharing UAV data using cloud optimized data 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 44 TB of initial datasets have been, or are in the process of being, collected for ingestion into the Data and Visualization Framework (presently 40 TB Purdue, 2.34 TB UGA, 1.5 TB UMaine) including: Indiana statewide LiDAR (2011–2013: Original point cloud in Cloud Optimized Point Cloud [COPC] format, Digital Surface Model [DSM] in Cloud Optimized Geotiff [COG] format, DTM in COG format, Normalized Digital Height Model [NDHM] in COG format and 2016–2019: COPC and DTM in COG formats) Indiana Statewide Orthoimagery (2011–2023: County-wide COG format; and 2020–2022 Indiana Data Harvest Program Vector Layers: Address Point layer, Parcels layer, Centerline layer); Southern GIS variously as vector data (13 states for roads USGS Topologically Integrated Geographic Encoding and Referencing [TIGER]), streams/watersheds, forestland ownership for FL and NC, Treemap, Soil (USDA Soil Survey Geographic Database [SSURGO]), Talladega National Forest (240 k acres in AL) as biomass, volume, basal area, LiDAR, imagery (USDA NAIP), boundary, soils, roads, 255 0.10-acre field measurement plots; UMaine mill locations, multi-scale forest carbon and timber projections through 2100, Forest Tool Data, Penobscot County, State of Maine and Eastern U.S. Cities Tree Localization dataset (collected location/distribution of all trees in Eastern U.S. cities with over 100 k population, from satellite data).

plans for the coming year, april 2024-march 2025

deliverables year 2

• Geospatial Information System

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 spaceborne platforms. The UMaine 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 Data 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.

Engaged, Data-Driven (Extension)

Engage stakeholders to develop climate-smart management practices that can improve the sustainability and resilience of forest ecosystems in the Eastern U.S., based on outcomes from Objective 1 and 2. We will deploy a use-inspired, co-production model of research and extension to facilitate both: (a) the successful development of the simulation/optimization system and (b) the actual adoption of climate-smart management practices by stakeholders to build environmentally and economically sustainable forests, especially on private lands in rural U.S.

Task 3.1 Stakeholder Perceptions (mo. 1-24): Develop and conduct a survey of foresters and forest landowners concerning current forest practices and environmental challenges, and their interests in ecosystem services and alternative future scenarios.

Task 3.2 Scenario Development (mo. 1-37): Co-develop (with stakeholders) “what-if” scenarios to examine current and future risk perceptions from climate change, available markets, or pests and the degree of support for forest management strategies.

Task 3.3 Focused Outreach (mo. 25-60): Assess end-user satisfaction through staggered, in-person or virtual participatory workshops with stakeholders across subregions to assess project outcomes and the general usability of the developed tools.

Task 3.4 Technology Application (mo. 25-60): Conduct training sessions for stakeholders on tool and system use. 

Deliverables Year 1

• Identify Stakeholder Needs
  • Initial
• Conduct What-If Scenarios
  • Initial

Accomplishments in Year 1

Task 3.1 Stakeholder Perceptions: As an initial step in identifying stakeholder needs (Deliverable #1), we initiated a literature review compilation of prior surveys of forest business owners, forestry professionals, and landowners on topics related to digital forestry. Year 1 outlined sampling frames for state-level data collection from these three main groups specifically concerning technology use and landowner typologies. We assessed qualitative and quantitative methods and determined that we would use a Delphi technique for understanding the perspectives of forestry experts followed by survey instruments for gathering the experiences of forestry professionals.

PERSEUS has 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 multiple rounds of data collection and analysis that aims to 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.” Round 1 of the Delphi process (with forestry professional stakeholders) was launched in February 2024 following Institutional Review Board (IRB) approval at UMaine. Preliminary 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: A literature search was similarly initiated to identify, collect, and review prior work in Maine, Georgia, and Indiana related to scenario development focused on forest products and ecosystem services. We assessed the model and what-if scenario framework developed in Maine for adaptation for the other states. The Maine framework (Deliverable #2) was developed and published (Zhao et al., 2023. Climate and socioeconomic impacts on Maine’s forests under alternative future pathways. DOI 10.1016/j.ecolecon.2023.107979). Informal discussions have begun with stakeholders (e.g., Cooperative Forestry Research Unit [CFRU], lumber associations) to host regional or cross-regional workshops to solicit input on scenario development.

PLANS FOR THE COMING YEAR, APRIL 2024—MARCH 2025

Deliverables Year 2

• Identify Stakeholder Needs
  • Final
• Conduct What-If Scenarios
  • Interim
• Remote Training Events
  • Initial

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 UGA and to be adapted for Maine and Indiana targeting forest businesses and industries, and the other led by Purdue and to be adapted for 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. 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.

DIGITAL COMPETENCE IN STUDENTS AND PROFESSIONALS (EDUCATION)

Develop a digitally-competent mindset in students and professionals for climate-smart natural resources management. We will actively train or retrain diverse cohorts of students and professionals through immersive learning experiences and online learning opportunities to modernize a skilled workforce. We will target recruitment at underrepresented minorities and underserved rural communities to diversify the voices engaged in forestry and to upskill those typically overlooked for such opportunities.

Task 4.1 Learning Communities (mo. 1-60): Design project-focused learning communities that provide opportunities for data-science/engineering undergraduates to work on forestry issues and for forestry undergraduates to learn digital technologies.

Task 4.2 Interns and Fellows (mo. 1-60): Provide undergraduate internships and graduate fellowships for students interested in digital forestry, recruiting and effectively engaging students with all aspects of the research project.

Task 4.3 Curriculum Development (mo. 1-60): Develop curriculum aimed at expanding the digital awareness of students engaged in forestry via a wide selection of transdisciplinary courses corresponding to the data pipeline in GIS science, UAVs and remote sensing, and data science. Develop a Professional MS in Digital Natural Resources.

Task 4.4 Online Certificate (mo. 25-60): Develop online, cross-institutional digital forestry curricula for certificates including the core digital forestry curriculum—undergraduate, graduate, bridging to professional science MS, and professional training, workforce development, Extension, etc.

Deliverables Year 1

• Establish Learning Communities
  • Initial
• Recruit Internships/Fellowships
  • Initial
• Proposed New Digital Forestry Cirriculum
  • Initial

Accomplishments in Year 1

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-institutional hybrid Learning Community consisting of an undergraduate student intern cohort experience (with academic-year and summer semester components) and a graduate student/postdoctoral researcher fellow 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 for advertising and best practices for recruiting and mentoring interns is being finalized, adopting and following best practices from other successful undergraduate intern programs (e.g., the National Science Foundation [NSF] Research Experiences for Undergraduates Program).

Task 4.2 Interns and Fellows: An undergraduate student intern experience is under development that will encompass a cohort experiential learning framework. A total of five undergraduate students have been employed at UGA and Purdue.

Task 4.3 Curriculum Development: A Big Data in Forestry course is being delivered at UMaine in Spring Term 2024. Titled “Enhanced Forest Inventory and Analysis,” this first offering of the course introduced seven 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 such as airborne LiDAR and satellite multispectral imaging. The hybrid format course is intended for a mix of traditional graduate students and postgraduates from the professional workforce.

Purdue is developing curriculum for an online Professional MS of Forestry in Digital Natural Resources Degree Program that will target working professionals looking to add skillsets focused on data acquisition, analysis, and application using next-generation approaches, including UAVs, environmental sensor networks, and remote sensing with LiDAR, multispectral imaging, and photogrammetry. Communications with industry and agency stakeholders indicate broad support and ample demand for this program. The proposal for this program is currently in preparation and will be 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 several workshops that provide instruction and hands-on experience with several of these technologies to PERSEUS students and postdoctoral researchers.

Task 4.4 Online Certificate: OLAF courses on remote sensing and AI are being developed by forestry and AI collaborators at UGA. Purdue and UMaine colleagues will provide feedback. Continuing education credits will be certified by the Society of American Foresters.

PLANS FOR THE COMING YEAR, APRIL 2024—MARCH 2025

Deliverables Year 2

• Establish Learning Communities
  • Interim
• Recruit Internships/Fellowships
  • Interim
• Propose New Digital Forestry Cirriculum
  • Interim

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 interns will 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 the Purdue online MS of Forestry in Digital Natural Resources Degree Program.

Publications Acknowledging PERSEUS Funding

Cordonnier, G., Jouvet, G., Peytavie, A., Braun, J., Cani, M.-P., Benes, B., Galin, E., Guérin, E., & Gain, J. (2023). Forming Terrains by Glacial Erosion. ACM Transaction on Graphics, 42(4). DOI: 10.1145/3592422

Lee, Jae Joong, Li, Bosheng, Benes, Bedrich. (2024) Latent L-systems: Transformer-based Tree Generator. ACM Transactions on Graphics. 43(102): pp 1–16. DOI: 10.1145/3627101.

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

Roy, S., Wei, X., Weiskittel, A., Hayes, D.J., Nelson, P., and 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

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.

Conference Presentations Referencing PERSEUS Research

Bettinger, P., K. Merry, C. Vatandaşlar, and T. Lee. Explaining AI and remote sensing to non-scientists using Online Learning in Applied Forestry (OLAF). Society of American Foresters National Convention. Sacramento, CA. October 27, 2023.

Lee, T., A. Peduzzi, C. Vatandaşlar, P. Bettinger, K. Merry, and J. Stober. Estimating forest attributes using airborne LiDAR and vegetation indices: Case study from a natural pine-dominated ecosystem in the Southeastern US. Society of American Foresters National Convention. Sacramento, CA. October 25, 2023.

Lee, T., A. Peduzzi, C. Vatandaşlar, P. Bettinger, K. Merry, and J. Stober. The effect of inherent positional error of GNSS receiver on the accuracy of models for estimating forest variables using airborne LiDAR. 14th Southern Forestry and Natural Resource Management GIS Conference. Athens, GA. December 11, 2023.

Merry, K., P. Bettinger, T. Lee, C. Vatandaşlar, and C. Merritt. OLAF: The Online Learning in Applied Forestry education tool. IUFRO Conference on Forest Knowledge Exchange: Advancing Innovation with Tradition. Padua, Italy. October 9, 2023.

Sankhe, A., C. Vatandaslar, P. Bettinger, F.W. Maier, and T. Lee. Automating forest stand delineation using AI integration of optical imagery, airborne LiDAR, and forest inventory. 2024 AI in Agriculture and Natural Resources Conference, April 15-17, 2024, College Station, TX.

Vatadaslar, C., T. Lee, A. Peduzzi, P. Bettinger, K. Merry, and J. Stober. Mapping ecological condition classes of a natural pine-dominated national forest in the southeastern U.S. In Proceedings of the IEEE International Symposium on Geoscience and Remote Sensing (IGARSS). The Institute of Electrical and Electronics Engineers, Inc., Piscataway, NJ. July 2023 pp. 2676-2679.

Other Products

Activities

February 2024 Purdue University Annual Ag Alumni Fish Fry. Digital Forestry, Songlin Fei

January 2024 MSU Forest Carbon and Climate Program 2023-24 Forests and Climate Learning Exchange Series. Assessing alternative modeling frameworks for carbon accounting in managed forests, Adam Daigneault, Daniel Hayes

December 2023 Purdue Data-Driven Seminars. Digital Forestry online platform for big geospatial data management and analysis, Jinha Jung

October 2023 Purdue University President’s Westwood Lecture Series, Songlin Fei

Events

April 2024 University of Georgia Institute for Artificial Intelligence AI Research Day: AI Transforming

February 2024 Purdue Institute for Digital Forestry Mini Symposium with PERSEUS

November 2023 PERSEUS All-Hands Fall Remote Meeting

November 2023 External Advisory Board Meeting

August 2023 PERSEUS All-Hands Launch Meeting

Publications

Chivhenge, E., Ray, D. G., Weiskittel, A. R., Woodall, C. W., & D’Amato, A. W. (2024). Evaluating the Development and Application of Stand Density Index for the Management of Complex and Adaptive Forests. Current Forestry Reports, 1-20.

Services

December 2023 Halderman Real Estate and Farm Management, Songlin Fei; digital forest management discussion.

Other

PERSEUS website

Spatio-Temporal Asset Catalog (STAC): https://stac.digitalforestry.org