The deadline to submit a session, town hall, or pre-conference workshop proposal for AGU25 has passed. Please search for and review proposed sessions below. Please note this site is frozen as of 4/29/25 and will not reflect any changes to proposals made after this date.


Conveners will be contacted by the AGU25 Program Committee with any requests for mergers or edits to proposals. Conveners will be notified of the acceptance of their proposal in mid-June.


Abstract submissions will also open in mid-June and the deadline for abstract submissions is 30 July, 2025.


Please visit the AGU25 website for more information or please contact AGU with any questions.

Session Proposal: Emerging Machine Learning Approaches for Process Understanding and Predictions in Ecosystem Sciences (AGU25)

B036
Emerging Machine Learning Approaches for Process Understanding and Predictions in Ecosystem Sciences

Session ID#: 248705

Session Description:
Rapid advances in machine learning are transforming ecosystem sciences, generating new insights into terrestrial, aquatic, and marine systems. Growing data availability, from ground-based measurements to remote sensing, increasingly enables data-driven discoveries. Integrating data-driven and process-based approaches, including physical laws and causal relationships, is driving fundamental and applied innovations to address land and resource management challenges posed by climate change.This session invites contributions that leverage cutting-edge machine learning to advance our understanding and management of ecosystems. Relevant areas include physics-informed machine learning, differentiable modeling, foundation models, generative AI, large language models, digital twins, causal inference, trustworthy AI, transfer learning, information theory, and uncertainty-aware modeling. We welcome applications spanning biogeochemistry, ecosystem services, agroecosystem modeling, biodiversity, conservation biology, nature-based climate solutions etc. This session aims to foster dialogues about the opportunities and considerations associated with AI applications to improve the understanding and prediction of ecosystem dynamics.
Co-Sponsor(s):
  • GC - Global Environmental Change
  • IN - Informatics
Index Terms:

0426 Biosphere/atmosphere interactions [BIOGEOSCIENCES]
0439 Ecosystems, structure and dynamics [BIOGEOSCIENCES]
1942 Machine learning [INFORMATICS]
1968 Scientific reasoning/inference [INFORMATICS]
Primary Convener:  Yanghui Kang, Virginia Tech, Department of Biological Systems Engineering, Blacksburg, United States
Conveners:  Maoya Bassiouni1, Trevor Keenan1 and Qing Zhu2, (1)University of California, Berkeley, Department of Environmental Science, Policy, and Management, Berkeley, United States(2)Lawrence Berkeley National Laboratory, Climate & Ecosystem Sciences Division, Berkeley, CA, United States
Student/Early Career Convener:  Doaa Aboelyazeed, Pennsylvania State University Main Campus, Department of Civil and Environmental Engineering, University Park, PA, United States
 
Parsimony versus complexity (Invited) (1859486)
Pierre Gentine1, Jianing Fang1, Wenli Zhao2 and Aya Lahlou3, (1)Columbia University, Department of Earth and Environmental Engineering, New York, United States, (2)Columbia University, Department of Earth and Environmental Engineering, New York, NY, United States, (3)Columbia University of New York, NSF Center for Learning the Earth with Artificial Intelligence and Physics, Palisades, United States
 
Monitoring the Early Growth of Pinus and Eucalyptus Plantations Using a Planet NICFI-Based Canopy Height Model: A Case Study in Southwest Brazil (1862207)
Fabien Hubert Wagner1, Fábio Marcelo Breunig2, Rafaelo Balbinot3, Emanuel Araújo Silva3, Messias Carneiro Soares3, Marco Antonio Kramm3, Mayumi Cursino de Moura Hirye4, Griffin Carter1, Ricardo Dalagnol1, Stephen Hagen1 and Sassan S Saatchi5, (1)CTrees, Pasadena, United States, (2)UFPR Federal University of Parana, Curitiba, Brazil, (3)UFSM Federal University of Santa Maria, Frederico Westphalen, Brazil, (4)University of California Los Angeles, Institute of the Environment and Sustainability, Los Angeles, United States, (5)JPL/NASA/Caltech, Carbon Cycle & Ecosystems/Earth Science, Pasadena, United States
 
Environmental Controls on Lespedeza cuneata Invasion in the U.S. Southern Great Plains: A Multi-Model Approach (1870238)
Smriti Shrestha1, Yuting Zhou1, Saber Brasher2, M. Saiful Islam1 and Hamed Gholizadeh1, (1)Oklahoma State University, Department of Geography, Stillwater, OK, United States, (2)National Snow and Ice Data Center, Boulder, United States
 
Process-Guided Interpretable Machine Learning for Ecosystem Dynamics: Modeling Biogeochemical Fluxes with Kolmogorov-Arnold Networks (1880606)
Zhangyu Wang, University of Maine, Orono, ME, United States and Yanghui Kang, University of Wisconsin Madison, Madison, United States
 
Exploring the Temperature Response of Nighttime Ecosystem Respiration in a Deciduous Broadleaf Forest Using Long-term Observations and Explainable AI (1883613)
Myunghan Son1, Youngryel Ryu2, Sungchan Jeong3 and Helin Zhang3, (1)Seoul National University, Seoul, Korea, Republic of (South), (2)Seoul National University, Department of Landscape Architecture and Rural Systems Engineering, Seoul, South Korea, (3)Seoul National University, Research Institute of Agriculture and Life Sciences, Seoul, South Korea
 
Modeling Photosynthesis and Plant Hydraulics Using a Differentiable Physics-Informed Machine Learning Framework (1886284)
Doaa Aboelyazeed1, Chonggang Xu2, Lianhong Gu3, Xiangzhong Luo4, Forrest Hoffman5, Jiangtao Liu6, Kathryn Lawson7 and Chaopeng Shen7, (1)Pennsylvania State University Main Campus, Department of Civil and Environmental Engineering, University Park, PA, United States, (2)Los Alamos National Lab, Los Alamos, United States, (3)Oak Ridge National Laboratory, Environmental Sciences Division, Oak Ridge, TN, United States, (4)Lawrence Berkeley National Lab, Department of Geography, Singapore, Singapore, (5)Oak Ridge National Laboratory, Computational Sciences & Engineering Division, Oak Ridge, United States, (6)Pennsylvania State University, Department of Civil and Environmental Engineering, University Park, United States, (7)Pennsylvania State University Main Campus, Department of Civil and Environmental Engineering, University Park, United States
 
A Physics-Informed ControlNet Framework for Global Ocean Chlorophyll Forecasting (1887799)
Jisook Park, Jeonbuk National University, Department of Environment and Energy, Jeonju, South Korea, Jong-Yeon Park, Jeonbuk National University, Department of Environment and Energy, Department of Earth and Environmental Sciences, Jeonju, South Korea and Yoo-Geun Ham, Seoul National University, Department of Environmental Planning, Graduate School of Environmental Studies, Seoul, South Korea
 
ALIVE-KGML: A Knowledge-Guided Machine Learning Framework for Coupled Carbon and Water Flux Estimation from Geostationary Satellites (1894296)
Sadegh Ranjbar, PhD Candidate, University of Wisconsin Madison, Biological Systems Engineering, Madison, United States, Danielle Losos, University of Wisconsin, SSEC/CIMSS, Madison, United States, Sophie Hoffman, University of Wisconsin Madison, Biological System Engineering, Madison, United States, Qunying Huang, University of Wisconsin Madison, Department of Geography, Madison, United States, Ankur R Desai, University of Wisconsin Madison, Atmospheric and Oceanic Sciences, Madison, United States and Paul C Stoy, University of Wisconsin-Madison, Madison, Biological Systems Engineering, Madison, United States
 
Investigating Snowpack-Shrub Interactions in the Arctic Tundra using Machine Learning and Process Models (1898345)
Isabella Lu, Columbia University, San Francisco, California, UNITED STATES, Linnia R Hawkins, Columbia University, Department of Earth and Environmental Engineering, New York, United States, Katherine Dagon, NSF National Center for Atmospheric Research, Boulder, United States, Mr. Sudhanshu Kumar, Auburn University, Department of Crop, Soil & Environmental Sciences, Auburn, United States and Sarah Ryu, University of California Berkeley, Department of Environmental Science, Policy, and Management, Berkeley, United States
 
A Flux Interpretation and Analysis Tool (FIAT) to Unravel Ecosystem Response to Environmental Conditions (1907324)
Xiuzhi Chen1, Jacob A Nelson2, Anke Hildebrandt3, Markus Reichstein1 and Martin Jung2, (1)Max Planck Institute for Biogeochemistry, Jena, Germany, (2)Max Planck Institute for Biogeochemistry, Department of Biogeochemical Integration, Jena, Germany, (3)Friedrich Schiller University of Jena, Ecological Modelling, Jena, Germany
 
Response of Global Photosynthesis to Climate Change based on Earth Observation and Machine Learning (1909685)
Rahul Kashyap, Indian Institute of Technology Kharagpur, Kharagpur, India and Jayanarayanan Kuttippurath, Indian Institute of Technology Kharagpur, Centre for Ocean, River, Atmosphere and Land Sciences, Kharagpur, India
 
abstract to delete (1912897)
Abdelghani Belgaid1, Oumnia Ennaji2 and Achraf El Allali1, (1)Mohammed VI Polytechnic University, College of Computing, Ben Guerir, Morocco, (2)Mohammed VI Polytechnic University, College of Computing & College of Agriculture and Environmental Sciences, Ben Guerir, Morocco
 
Predicting Storm Surge Impacts on Avian Biodiversity Using Spatial Temporal Adaptive Ensemble Deep Learning Models (1933514)
Liying Li, University of California Santa Barbara, National Center for Ecological Analysis and Synthesis, Santa Barbara, United States
 
Assessing Forest Health and Ecosystem Services at Scale: Novel Lightweight AI Architectures for Accessible Remote Sensing–Driven Decision Support (1934421)
Cibele H Amaral1,2, Jerry Gammie1,3, Erick Verleye1,2, Nayani Thanuja Ilangakoon1, Anna LoPresti4, E. Natasha Stavros5, Claire Monteleoni2,3 and Laura E Dee4, (1)University of Colorado Boulder, CIRES, Earth Lab, Boulder, United States, (2)University of Colorado Boulder, CIRES, ESIIL, Boulder, United States, (3)University of Colorado Boulder, Computer Science, Boulder, United States, (4)University of Colorado Boulder, Ecology & Evolutionary Biology, Boulder, United States, (5)WKID Solutions, Boulder, United States
 
PREDICTION OF CARBON EXCHANGES OF A FORESTED AND A GRASSLAND ECOSYSTEM OF HIMALAYA: A COMPARATIVE ASSESSMENT USING MACHINE LEARNING CLASSIFIERS (1938611)
Priyanka Lohani, GB Pant National Institute of Himlayan Environment, Ladakh Regional Centre, Leh, India and Sandipan Mukherjee, Ladakh Regional Centre, G. B. Pant National Institute of Himalayan Environment, Leh 194101, Ladakh Union Territory, India, Leh, India
 
Importance of soil moisture temporal scale, depth, and antecedent conditions for machine-learning based predictions of dryland carbon and water fluxes (1940231)
Rubaya Pervin1, Mallory Barnes2, Scott Robeson2, Steve Kannenberg3, Jie Hu4 and Natasha MacBean5, (1)Indiana University Bloomington, Bloomington, IN, United States, (2)Indiana University Bloomington, Bloomington, United States, (3)West Virginia University, Morgantown, United States, (4)West Virginia University, Biology, Morgantown, United States, (5)Western University, Department of Geography & Environment and Department of Biology, London, Canada
 
Uncovering Soil Organic Carbon Saturation and Protection Mechanisms: Parameter Learning on Multiple Sparse Data Sources with Comprehensive Uncertainty Estimation (1944499)
Leo Roßdeutscher1, Katerina Georgiou2, William J Riley3, Mohammed Chettouh1, Thomas Wutzler1, Marion Schrumpf1, Markus Reichstein1 and Bernhard Ahrens1, (1)Max Planck Institute for Biogeochemistry, Jena, Germany, (2)Oregon State University, Corvallis, United States, (3)Lawrence Berkeley National Laboratory, Climate and Ecosystem Sciences Division, Berkeley, United States
 
Physically Interpretable Machine Learning for Wildfire Prediction in the Western US (Invited) (1950729)
Dr. Fa Li, Stanford University, Earth System Science, Stanford, United States, Min Chen, University of Wisconsin Madison, Forest and Wildlife Ecology, Madison, WI, United States and Qing Zhu, Lawrence Berkeley National Laboratory, Climate & Ecosystem Sciences Division, Berkeley, CA, United States
 
From Pixels to Predictions: Prithvi-EO-2.0 for Land, Disaster, and Ecosystem Intelligence (Invited) (1953011)
Sujit Roy1, Daniela Szwarcman2, Paolo Fraccaro3, Manil Maskey4, Rahul Ramachandran1 and Prithvi EO 2.0 Team, (1)NASA Marshall Space Flight Center, Huntsville, United States, (2)IBM Research, Rio de Janeiro, Brazil, (3)IBM Research, Daresbury, United Kingdom, (4)NASA, Huntsville, United States
 
Machine Learning-Based Optimization of Site-Specific Fertilizer Recommendation (1953967)
Oumnia Ennaji1, Abdelghani Belgaid2 and Achraf El Allali2, (1)Mohammed VI Polytechnic University, College of Computing & College of Agriculture and Environmental Sciences, Ben Guerir, Morocco, (2)Mohammed VI Polytechnic University, College of Computing, Ben Guerir, Morocco
 
Estimation of Key Photosynthetic Parameters through Machine Learning (1954785)
Ruhaan Singh1, Ms. Morgan Steckler2, Forrest Hoffman3, Elias Massoud3, Nathan Collier3 and Jitendra Kumar4, (1)Farragut High School, Knoxville, United States, (2)Oak Ridge National Laboratory, Oak Ridge, TN, United States, (3)Oak Ridge National Laboratory, Computational Sciences & Engineering Division, Oak Ridge, United States, (4)Oak Ridge National Laboratory, Oak Ridge, United States
 
High-Resolution Carbon Flux Monitoring using a Global Estimation Model (CARBON-GEM) in Google Earth Engine (1960776)
Emma Izquierdo1, Alvaro Moreno2, Jordi Muñoz2, Johanes Hirn2, Laura Martínez-Ferrer2 and Gustau Camps-Valls2, (1)BOKU University, Institute of Geomatics, Vienna, Austria, (2)Image Processing Laboratory, Universitat de València, Paterna, Spain
 
Using Machine Learning to Detect Seals and Polar Bears in Multispectral Aerial Imagery (1961699)
Leah Porras, NOAA EPP/MSI CESSRST-II, Electrical and Computer Engineering, El Paso, United States, Erin Moreland, NOAA Seattle, Seattle, United States and Miguel Velez-Reyes, The University of Texas at El Paso, Electrical and Computer Engineering, El Paso, United States
 
Next-Generation Modeling of Global Natural Methane Fluxes: Integrating Multi-scale Observations with Knowledge-Guided Machine Learning (1967563)
Youmi Oh1,2, Licheng LIU3, Qing Zhu4, Sparkle L Malone5, Gavin McNicol6, Chris Smith7, Shuo Chen8, Yiming Sun9, Avni Malhotra10, Bradley Gay11, Colin A Quinn12, Eric Ward13, Dr. Fa Li14, Fenghui Yuan15, Jianqiu Zheng10, Kendalynn Morris16, Kevin Rozmiarek17, Kunxiaojia Yuan4, Kyle Andreas Arndt18, Lori Bruhwiler1, Qing Ying19, Stefan Metzger20,21, Yi Yang22 and ESIIL AI for Natural Methane Working Group, (1)NOAA, Global Monitoring Laboratory, Boulder, United States, (2)University of Colorado Boulder, Cooperative Institute for Research in Environmental Sciences, Boulder, United States, (3)University of Minnesota Twin Cities, Department of Bioproducts and Biosystems Engineering, Saint Paul, United States, (4)Lawrence Berkeley National Laboratory, Climate & Ecosystem Sciences Division, Berkeley, CA, United States, (5)Yale University, New Haven, United States, (6)University of Illinois Chicago, Earth and Environmental Sciences, Chicago, United States, (7)University of Colorado Boulder and NOAA Global Monitoring Laboratory, Boulder, United States, (8)Purdue University, Department of Earth, Atmospheric, and Planetary Sciences, West Lafayette, United States, (9)University of Pittsburgh, Pittsburgh, United States, (10)Pacific Northwest National Laboratory, Richland, WA, United States, (11)NASA GSFC/UMD ESSIC, Greenbelt, United States, (12)NASA GSFC/UMD ESSIC, Biospheric Sciences, College Park, United States, (13)NASA GSFC/UMD ESSIC, College PARK, United States, (14)Stanford University, Earth System Science, Stanford, United States, (15)University of Minnesota Twin Cities, Department of Soil, Water, and Climate, St. Paul, United States, (16)Pacific Northwest National Laboratory, Joint Global Change Research Institute, College Park, United States, (17)University of Colorado Boulder, Institute of Arctic and Alpine Research, Boulder, United States, (18)Woodwell Climate Research Center, Falmouth, United States, (19)NASA GSFC/UMD ESSIC, College Park, United States, (20)University of Wisconsin Madison, Dept of Atmospheric and Oceanic Sciences, Madison, United States, (21)AtmoFacts, Longmont, United States, (22)Colorado State University, Natural Resource Ecological Laboratory, Fort Collins, CO, United States
 
Leveraging Memory in Deep Learning to Improve Drought Impact and Legacy Predictions in Forest Ecosystems (1970082)
Jingyi Bu, University of New Hampshire Main Campus, Durham, NH, United States, Claire Xiao, Phillips Exeter Academy, Exeter, United States, Jiangtao Liu, Pennsylvania State University, Department of Civil and Environmental Engineering, University Park, United States, J. William Munger, School of Engineering and Applied Sciences and Department of Earth and Planetary Sciences, Harvard University, Cambridge, MA, USA, Cambridge, United States and Jingfeng Xiao, University of New Hampshire, Institute for the Study of Earth, Oceans, and Space, Earth Systems Research Center, Durham, United States
 
A Hybrid Modeling Approach to Global Water–Carbon Cycles Informed by Atmospheric and Terrestrial Observations (1970668)
Zavud Baghirov1, Markus Reichstein2, Basil Kraft3, Bernhard Ahrens2, Marco Körner4 and Jung Martin5, (1)Max Planck Institute for Biogeochemistry, Biogeochemical Integration, Jena, Germany, (2)Max Planck Institute for Biogeochemistry, Jena, Germany, (3)ETH Zurich, Environmental Systems Science, Zurich, Switzerland, (4)Technical University of Munich, Department of Aerospace and Geodesy, School of Engineering and Design, Munich, Germany, (5)Max Planck Institute for Biogeochemistry, Department of Biogeochemical Integration, Jena, Germany
 
Assessing the best modeling technique among linear, nonlinear, and artificial intelligence models for estimating the age of longleaf pine (Pinus palustris Mill.) trees from terrestrial laser scanning (1972111)
Kody Brock1, Kleydson Diego Rocha2, Ana Paula Corte3, Ajay Sharma4, Jeffery Cannon5, Cesar Ivan Alvites Diaz2, Mauro Alessandro Karasinski6, Rodrigo Vieira Leite7, Monique Bohora Schlickmann2, Jinyi Xia8, Jason Vogel2, Jeff Atkins9, Aditya Sing10, Andrew T Hudak11, Carine Klauberg2, Andrew J. Sanchez Meador12, Carlos Alberto Silva2 and Adrián Cardil13, (1)University of Florida, School of Forest, Fisheries, and Geomatics Sciences, Gainsville, United States, (2)University of Florida, School of Forest, Fisheries and Geomatics Sciences, Gainesville, United States, (3)BIOFIX, Universidade Federal do Paraná, Avenida Prefeito Lothario Meissner, 632, Jardim Botânico, Curitiba, PR, BR 80210-170,, Curitiba, Brazil, (4)Auburn University, Auburn, United States, (5)Joseph W. Jones Ecological Research Center, Newton, United States, (6)University of Florida, School of Forest, Fisheries, and Geomatics Sciences, Gainesville, United States, (7)PUC Pontifical Catholic University of Rio de Janeiro, Rio De Janeiro, Brazil, (8)University of Florida, School of Forest, Fisheries and Geomatics Sciences, Ft Walton Beach, FL, United States, (9)Virginia Commonwealth University, Biology, Richmond, United States, (10)Caesar Kleberg Wildlife Research Institute, Kingsville, United States, (11)USDA Forest Service, Rocky Mountain Research Station, Moscow, United States, (12)Northern Arizona University, Ecological Restoration Institute and School of Forestry, Flagstaff, United States, (13)Technosylva, Fire Science, León, Spain
 
Spatiotemporal Interrogation of Crop Yield Patterns to Identify Key Variables and Feature Interactions using a Tandem Evolutionary Algorithm (1974284)
Ali Dadkhah1, Donna M Rizzo2, Paul R Adler3, Ryan van der Heijden4, Matthew W Myers3, Jitender Rathore5, Luis A Garcia1, George F Pinder1, Kristen Underwood6, John Hanley7 and Asim Zia8, (1)University of Vermont, Department of Civil and Environmental Engineering, Burlington, VT, United States, (2)University of Vermont, Department of Civil and Environmental Engineering, Burlington, United States, (3)USDA-ARS, Pasture Systems and Watershed Management Research Unit, University Park, United States, (4)University of Vermont, Civil & Environmental Engineering, Burlington, VT, United States, (5)Virginia Polytechnic Institute and State University, School of Plant and Environmental Sciences, Blacksburg, United States, (6)University of Vermont, Civil & Environmental Engineering; Water Resources Institute, Burlington, United States, (7)Data Scientist, Special Olympics International, Washington, DC, United States, (8)University of Vermont, Department of Community Development and Applied Economics, Department of Computer Science, Burlington, VT, United States
 
Uncertainty-Aware Tillage Mapping in Data-Limited Agroecosystems. (1978108)
Amin Norouzi1, Mohammed Amine Gharsallaoui2, Janardhan Rao Doppa3 and Kirti Rajagopalan1, (1)Washington State University, Biological Systems Engineering, Pullman, WA, United States, (2)Washington State University, EECS, Pullman, WA, United States, (3)Washington State University, EECS, Pullman, United States
 
CarbonSense/EcoPerceiver 2.0: Multimodal Deep Learning for Global Hourly Flux Modelling (1991801)
Matteo Detto1, Matthew Fortier2, Luis Lara2, Mathias La Rochelle3, Oliver Sonnentag4 and Christopher Pal5, (1)Princeton University, High Meadows Environmental Institute, Princeton, NJ, United States, (2)Mila - Quebec Artificial Intelligence Institute, Montreal, Canada, (3)Université de Montréal, Montréal, Canada, (4)University of Montreal, Département de Géographie, Montreal, QC, Canada, (5)Ecole Polytechnique de Montreal, Computer Engineering and Software Engineering, Montreal, Canada
See more of: Biogeosciences
<< Previous Session Proposal | Next Session Proposal >>