B020
Bridging Remote Sensing, Machine Learning, and Ecological Modeling to Address Forest Health Challenges
Session ID#: 247857
Session Description:
Forests worldwide face threats from pests, pathogens, invasive species, human activities, and rapid environmental change—challenges that impair forest health, biodiversity, and essential ecosystem services. Despite extensive evidence of these impacts, the best strategies to protect, monitor, and manage forests remain uncertain, underscoring the need for integrated, interdisciplinary solutions. This session aims to: 1) showcase research using remote sensing, machine and deep learning, and mathematical modeling to enhance understanding, prediction, and management of forest health; and 2) promote interdisciplinary collaboration and discussion of scientific advances and real-world applications to improve ecosystem sustainability, guide forest management policies, and mitigate societal impacts. We invite presentations on novel machine learning methods for detecting forest diseases, advances in integrating remote sensing with ecological models, practical applications that improve forest management, rigorous evaluations of model uncertainty, and studies on climate change impacts on forest ecosystems.
Index Terms:
0434 Data sets [BIOGEOSCIENCES]
0466 Modeling [BIOGEOSCIENCES]
0476 Plant ecology [BIOGEOSCIENCES]
0480 Remote sensing [BIOGEOSCIENCES]
Primary Convener: Yorkinoy Shermatova, University of Minnesota Twin Cities, Minneapolis, MN, United States
Conveners: Jesus N Pinto Ledezma, University of Minnesota Twin Cities, Dept. of Ecology, Evolution and Behavior, Minneapolis, MN, United States and Jeannine Cavender-Bares, Harvard University Herbaria, Organismic and Evolutionary Biology, Cambridge, United States
Student/Early Career Convener: Yorkinoy Shermatova, University of Minnesota Twin Cities, Minneapolis, MN, United States
Autocorrelation, not ecological context, drives tree mortality forecasts at continental scale (1865988)
Keenan Ganz1, Liz Van Wagtendonk1, Pratima K C2 and L. M. Moskal1, (1)University of Washington Seattle Campus, School of Environmental and Forest Sciences, Seattle, United States, (2)Bay Area Environmental Research Institute, Moffett Field, United States
Hyperspectral detection of foliar chemistry in aspen to detect infection by two cankers (1893842)
Porter Reim1, Ewa Czyz2, Amy Trowbridge1, Celso Olivera3 and Philip A Townsend1, (1)University of Wisconsin Madison, Department of Forest and Wildlife Ecology, Madison, United States, (2)JPL/NASA/Caltech, Earth Science, Pasadena, United States, (3)University of Wisconsin-Madison, Department of Entomology, Madison, United States
Data Assimilation for Forest Pathogen Forecasting: Fusing Phenological Remote Sensing Outputs and Spatial Kernels in Oak Wilt Epidemiology (1896255)
Yorkinoy Shermatova, University of Minnesota Twin Cities, Minneapolis, MN, United States, Jesus N Pinto Ledezma, University of Minnesota Twin Cities, Dept. of Ecology, Evolution and Behavior, Minneapolis, MN, United States, Jeannine Cavender-Bares, Harvard University, Department of Organismic and Evolutionary Biology, Cambridge, United States and Jesús Pinto-Ledezma
A daily, long-term, microwave remote sensing-informed dataset of live fuel moisture content from machine learning (1940654)
Trent W Robinett1, Emil Biju2,3, Dapeng Feng4,5 and Alexandra G Konings2, (1)Stanford University, Stanford, CA, United States, (2)Stanford University, Earth System Science, Stanford, United States, (3)Microsoft Corporation, Redmond, United States, (4)Stanford University, Earth System Science, Stanford, CA, United States, (5)Stanford University, Institute for Human-Centered Artificial Intelligence, Stanford, CA, United States
Combined Multi-scale, Multi-modal Observations to Detect Invasive Plants and Elucidate Their Ecological Impacts (1955468)
Kelsey Susanne Huelsman, Earth Resources Technology Inc, Laurel, MD, United States, Dr. Shawn Serbin, BA, MS, PhD, Brookhaven National Laboratory, Environmental Science and Technologies Department, Upton, United States, Kristen Lewers, University of Colorado at Boulder, Boulder, United States and Natalia Leonor Quinteros Casaverde, City University of New York & The New York Botanical Garden, Biology, New York, United States
Mapping Tree Mortality and Burn Severity Using Deep Learning: A Case Study on the 2020 Creek Fire (1967339)
Pratima K C, NASA Ames Research Center, Moffett Field, CA, United States, Liz Van Wagtendonk, Seattle, Washington, United States and Van R Kane, University of Washington Seattle Campus, School of Environmental and Forest Sciences, Seattle, United States
Integrating Ground and Aerial Data: Continental-Scale Mapping of Forest Biodiversity across the U.S. National Ecological Observatory Network (1970382)
Zhuohong Li1, Georgiy Zemlevskiy2, Sophie Mao2, Hashim Alrefaei2,3, Daniel Murong2, Hanshi Chen1 and Tong Qiu1, (1)Duke University, Nicholas School of the Environment, Durham, NC, United States, (2)Duke University, Durham, United States, (3)King Abdulaziz University, Jeddah, Saudi Arabia
Improving LAI Estimation in Broadleaf Forests via Deep-Learning DHP image Segmentation with Woody-Component Removal (1979468)
Jiwon Lee1, Jaese Lee1, Woohyeok Kim2, Yoojin Kang1 and Jungho Im2, (1)Ulsan National Institute of Science and Technology, Department of Civil, Urban, Earth, and Environmental Engineering, Ulsan, South Korea, (2)Ulsan National Institute of Science and Technology, Ulsan, South Korea
CHMer (Canopy Height Model-er): Leveraging Deep Learning for Site-Specific Sub-MeterCanopy Height Predictions (1979652)
Mia Mitchell1,2, Charles Abolt3, Zachary Crennen4, Agnese Marcato4 and Adam L Atchley4, (1)Los Alamos National Laboratory, Earth and Environmental Sciences, Los Alamos, NM, United States, (2)University of Washington, School of Environmental and Forest Sciences, Seattle, United States, (3)The Freshwater Trust, Science and Analytics Team, Portland, United States, (4)Los Alamos National Laboratory, Earth and Environmental Sciences, Los Alamos, United States
California Carbon Explorer: an Open-Source Platform for Visualizing Modeled Forest Carbon Cycle Dynamics with CARDAMOM (1984756)
Lily Klinek1, Jessie Au1,2, Thomas Luke Smallman2, David T Milodowski3, Mathew Williams2, A. Anthony Bloom4 and Troy Magney5, (1)University of California Davis, Department of Plant Sciences, Davis, CA, United States, (2)University of Edinburgh, School of GeoSciences, Edinburgh, United Kingdom, (3)University of Edinburgh, School of Geosciences, Edinburgh, United Kingdom, (4)Jet Propulsion Laboratory, California Institute of Technology, Pasadena, United States, (5)University of Montana, W.A. Franke College of Forestry and Conservation, Missoula, United States
Automated Norway Spruce Tree Detection and Delineation Using Fused YOLO-SAM Model with UAV Data (2003353)
Sudeep Kuikel1, Xuelian Meng1, Shangharsha Thapa2 and Per Ola Olsson2, (1)Louisiana State University, Department of Geography and Anthropology, Baton Rouge, United States, (2)Lund University, Department of Physical Geography and Ecosystem Science, Lund, Sweden
