B059
Leveraging Artificial Intelligence Tools to Couple Models and Experiments for Enhanced Ecosystem Predictability
Session ID#: 250295
Session Description:
Environmental systems exhibit complex heterogeneity requiring innovative approaches for predictive understanding across scales. Iterative coupling of models and experiments (ModEx) can help address knowledge gaps in heterogeneous environments by identifying key variables, optimizing data collection and enhancing an overall mechanistic understanding. Artificial intelligence and machine learning (AI/ML) can expedite the model-experiment cycle enabling researchers to fill data gaps, guide experimental design, and improve model calibration in ways that were previously impossible. This session explores how AI/ML facilitates the coupling between models and experiments in ecosystem sciences. We welcome contributions demonstrating innovative AI/ML applications that bridge observations and models across terrestrial, aquatic, and coastal environments. Submissions may address any ecosystem process including carbon and nutrient cycling, hydrology, plant-soil-microbe interactions, coastal dynamics, disturbance responses, and biogeochemical transformations. We encourage work highlighting experimental design optimization, and real-time model-experiment integration that overcome heterogeneity challenges and accelerate predictive understanding.
Co-Sponsor(s):
Index Terms:
0439 Ecosystems, structure and dynamics [BIOGEOSCIENCES]
1895 Instruments and techniques: monitoring [HYDROLOGY]
1920 Emerging informatics technologies [INFORMATICS]
1942 Machine learning [INFORMATICS]
Primary Convener: Vanessa Alessandra Garayburu-Caruso, Pacific Northwest National Laboratory, Environmental Molecular Sciences Laboratory, Richland, United States
Conveners: Avni Malhotra, Pacific Northwest National Laboratory, Richland, WA, United States, Dipankar Dwivedi, Lawrence Berkeley National Laboratory, Earth and Environmental Sciences Area, Berkeley, CA, United States and Pamela Weisenhorn, Argonne National Laboratory, Lemont, IL, United States
Student/Early Career Convener: Allison Myers-Pigg, Pacific Northwest National Laboratory, Richland, United States
Accelerating the Scientific Learning Cycle: AI-powered Integration of Models, Data and Experiments for Environmental System Science (Invited) (1854227)
Xingyuan Chen, Pacific Northwest National Laboratory, Richland, United States, Peishi Jiang, University of Alabama, Civil, Construction and Environmental Engineering, Tuscaloosa, AL, United States, Sundar Niroula, University of Illinois at Urbana-Champaign, Civil and Environmental Engineering, Urbana, United States and Faria T Zahura, University of Virginia, Charlottesville, United States
AI Frameworks to Enhance Predictability of Biogeochemical and Hydrologic Processes (Invited) (1935032)
Praveen Kumar1,2, Antoine Dolant3, Aramide Moronfoye3, Tarun Agrawal4, Harsh Shah4 and Allison Eva Goodwell5, (1)University of Illinois at Urbana-Champaign, Department of Civil and Environmental Engineering, Urbana, United States, (2)Prairie Research Institute at University of Illinois at Urbana-Champaign, Champaign, United States, (3)University of Illinois at Urbana-Champaign, Urbana, IL, UNITED STATES, (4)University of Illinois at Urbana Champaign, Civil and Environmental Engineering, Urbana, United States, (5)Prairie Research Institute at University of Illinois at Urbana-Champaign, Illinois State Water Survey, Champaign, United States
Transforming multiscale grain size mapping with modular AI and video surveys (1961862)
Yunxiang Chen, PhD1, Jie Bao1, Lupita Renteria2, Bing Li3 and James Stegen1, (1)Pacific Northwest National Laboratory, Richland, WA, United States, (2)Pacific Northwest National Laboratory, Richland, United States, (3)University of California Riverside, Riverside, United States
Methane and Microbes in the High Antarctic: Integrating Targeted Experiments with Deep Learning to Resolve Biogeochemical Mechanisms (1973453)
Jacob Wynne, University of California Santa Barbara, Ecology, Evolution and Marine Biology Department, Santa Barbara, CA, United States, Nima Azbijari, Oregon State University, Microbiology and Department of Electrical Engineering and Computer Science, Corvallis, United States, Maude David, Oregon State University, Microbiology, Corvallis, United States and Andrew Thurber, University of California Santa Barbara, Ecology, Evolution and Marine Biology Department, Santa Barbara, United States
From Barn to Model: Evaluating Manure-Specific CO₂ and GHG Emissions Using AI and Machine Learning Approaches (2000142)
Atikur Rahman1, Ali Fares1, Symum Islam1, Madison Celestine1, Ripendra Awal2, Anoop Valiya veettil1, Anwar Adem3, Nta-Akare Ausaji3 and Almoutaz Elhassan3, (1)Prairie View A & M University, Cooperative Agricultural Research Center, Prairie View, United States, (2)Prairie View A & M University, Cooperative Agricultural research center, Prairie View, United States, (3)Prairie View A & M University, Prairie View, United States
Integrating Transformer-Based Land Surface Phenology into the Community Land Model for Climate-Responsive Vegetation Dynamics (2003866)
Aya Lahlou1, Linnia R Hawkins2, Adrianna Foster3, David M Lawrence4 and Pierre Gentine2, (1)Columbia University of New York, NSF Center for Learning the Earth with Artificial Intelligence and Physics, Palisades, United States, (2)Columbia University, Department of Earth and Environmental Engineering, New York, United States, (3)University of Virginia Main Campus, Charlottesville, United States, (4)NSF National Center for Atmospheric Research, Boulder, United States
