B024
Emerging Machine Learning Approaches for Process Understanding in Ecosystem Sciences

Session ID#: 161448

Session Description:
Rapid advances in machine learning are transforming many areas of biogeosciences. Beyond traditional successes of machine learning in making predictions, novel combinations of data-driven and process-based approaches are generating new insights and accelerating scientific discoveries about terrestrial, aquatic, and marine ecosystems. Efficiency, interpretability, mechanistic understanding, and uncertainty quantification are among the key benefits of these new synergies.

In this session, we invite contributions that leverage emerging machine learning, artificial intelligence, and data science approaches to deepen our understanding and build generalized representations of ecosystem processes across all scales. Example areas include but are not restricted to applications of physics-informed machine learning, explainable machine learning, causal inference, information theory, unsupervised machine learning, Bayesian approaches, and uncertainty quantification. The focus of this session is on applications that provide novel understanding. Method development, reviews, syntheses, perspectives, and theoretical analyses are also welcome.

Index Terms:

0414 Biogeochemical cycles, processes, and modeling [BIOGEOSCIENCES]
0426 Biosphere/atmosphere interactions [BIOGEOSCIENCES]
1813 Eco-hydrology [HYDROLOGY]
1942 Machine learning [INFORMATICS]

Primary Convener:  Yanghui Kang, University of California, Berkeley, Department of Environmental Science, Policy, and Management, Berkeley, United States
Conveners:  Trevor F Keenan, University of California, Berkeley, Department of Environmental Science, Policy, and Management, Berkeley, United States, Gustau Camps-Valls, Image Processing Laboratory, Universitat de València, Paterna, Spain and Pierre Gentine, Columbia University, Department of Earth and Environmental Engineering, New York, NY, United States
Student/Early Career Convener:  Maoya Bassiouni, University of California, Berkeley, Department of Environmental Science, Policy, and Management, Berkeley, United States
 
Knowledge-guided machine learning for the next generation of agroecosystem prediction (Invited) (1044260)
Zhenong Jin1, Licheng LIU2, Qi Yang3, Kaiyu Guan4, Rahul Ghosh5, Xiaowei Jia6, Chongya Jiang7, Bin Peng8, Jinyun Tang9, Shaoming Xu5, Junxiong Zhou1, Wang Zhou8, Qing Zhu10 and Vipin Kumar11, (1)University of Minnesota Twin Cities, Department of Bioproducts and Biosystems Engineering, Saint Paul, United States, (2)University of Minnesota-Twin Cities, Department of Bioproducts and Biosystems Engineering, Saint Paul, United States, (3)University of Minnesota, St Paul, United States, (4)University of Illinois at Urbana Champaign, Department of Natural Resources and Environmental Sciences, College of Agricultural, Consumer and Environmental Sciences, Urbana, United States, (5)University of Minnesota-Twin Cities, Department of Computer Science/Engineering, Minneapolis, United States, (6)University of Pittsburgh, Department of Computer Science, Pittsburgh, PA, United States, (7)University of Illinois at Urbana Champaign, Agroecosystem Sustainability Center, Institute for Sustainability, Energy, and Environment, Urbana, IL, United States, (8)University of Illinois at Urbana Champaign, Agroecosystem Sustainability Center, Institute for Sustainability, Energy, and Environment, Urbana, United States, (9)Lawrence Berkeley Natl Lab, Climate and Ecosystem Sciences Division, Berkeley, United States, (10)Lawrence Berkeley National Laboratory, Berkeley, CA, United States, (11)University of Minnesota Twin Cities, Department of Computer Science/Engineering, Minneapolis, MN, United States
 
Plant access to belowground moisture allows sustained evapotranspiration during drought (1053553)
Francesco Giardina1,2, Pierre Gentine3,4, Alexandra G Konings5 and Benjamin Stocker1,6, (1)WSL Swiss Federal Institute for Forest, Snow and Landscape Research, Birmensdorf, Switzerland, (2)ETH Zürich, Department of Environmental Systems Science, Zürich, Switzerland, (3)Columbia University, Department of Earth and Environmental Engineering, New York, NY, United States, (4)Columbia University, Center for Learning the Earth with Artificial intelligence and Physics (LEAP), New York, United States, (5)Stanford University, Department of Earth System Science, Stanford, CA, United States, (6)ETH Zürich, Department of Environmental System Science, Zürich, Switzerland
 
Sensitivity Analysis and Uncertainty Quantification of E3SM Methane model using Machine Learning (1063227)
Sandeep Chinta, Massachusetts Institute of Technology, Cambridge, MA, United States, Xiang Gao, Massachusetts Institute of Technology, Joint Program on the Science and Policy of Global Change, Cambridge, MA, United States and Qing Zhu, Lawrence Berkeley National Laboratory, Climate & Ecosystem Sciences Division, Berkeley, CA, United States
 
Use Machine Learning Method to Improve Biological Aerosol Classification from Real-time Bioaerosol Sensing Measurements (1076438)
Yingxiao Zhang, University of Michigan Ann Arbor, Department of Climate and Space Sciences and Engineering, Ann Arbor, MI, United States, Zezhen Cheng, University of Georgia, Athens, United States, Nurun Nahar Lata, Michigan Technological University, Houghton, United States and Swarup China, Pacific Northwest National Laboratory, Richland, WA, United States
 
Combining randomized field experiments with observational satellite data to assess the benefits of crop rotations on yields (1100366)
Dan Kluger, Stanford, Statistics, Stanford, CA, United States, Art B Owen, Stanford University, Stanford, United States and David B Lobell, Stanford University, Stanford, CA, United States
 
Linking machine learning with remote sensing and process-based model to predict fluxes in a row crop agriculture. (1113881)
Bruno Basso, Michigan State University, Department of Earth and Environmental Sciences, East Lansing, United States and Prateek Sharma, Michigan State University, East Lansing, MI, United States
 
Crop Yield Prediction Using Remotely Sensed Derived Primary Production and Deep Learning (1115498)
Shahid Nawaz Khan and Dapeng Li, Geospatial Sciences Center of Excellence, Department of Geography and Geospatial Sciences, South Dakota State University, Brookings, SD 57007, USA, Brookings, United States
 
Generating gridded crop yields combining machine learning and spatial disaggregation over Mainland China from 2000 to 2016 (1133772)
Shuo Chen1,2, Weihang Liu2, Yiqing Liu2 and Tao Ye2, (1)Purdue University, West Lafayette, IN, United States, (2)Beijing Normal University, Beijing, China
 
Application of Machine Learning Approaches to Predict Soil Inorganic Carbon in Drylands (1135849)
Zahra Ghahremani, Boise State University, Department of Geoscience, Boise, United States, Jennifer L Pierce, Boise State University, Boise, ID, United States, David Huber, University of Texas at El Paso, Department of Earth, Environmental and Resource Sciences, El Paso, United States; USDA-ARS, Northwest Watershed Research Center, Boise, United States and Christopher Stanbery, Boise state University, Boise, United States
 
An AI Approach to Understanding Soil Health and Nutrient Cycling (1136132)
Alexandria Kuhl1, Andrew J. Margenot2, Jingrui He2, Hanghang Tong2, Supratik Guha1, Michael Douglass2, J Kemner2 and Roser Matamala3, (1)University of Chicago, Chicago, IL, United States, (2)University of Illinois at Urbana Champaign, Urbana, IL, United States, (3)Argonne National Laboratory, Environmental Science Division, Lemont, United States
 
Data-driven Soil Dynamics: Linking Moisture, Temperature and Respiration (1142224)
Doran Khamis, UNITED STATES, Matthew Fry, UK Centre for Ecology and Hydrology, Wallingford, United Kingdom, Hollie Cooper, CEH, Wallingford, United Kingdom, Ross Morrison, Centre for Ecology & Hydrology, Wallingford, United Kingdom and Eleanor Blyth, UK Centre for Ecology & Hydrology, Wallingford, United Kingdom
 
AI-based prediction of Alaskan natural fires and its application into NCAR community land model 5 - biochemistry (1142573)
Hocheol Seo and Yeonjoo Kim, Yonsei University, Department of Civil and Environmental Engineering, Seoul, Korea, Republic of (South)
 
High-resolution seasonal livestock distribution data on the Qinghai-Tibet Plateau in 2020 (1146012)
Ning Zhan, Weihang Liu and Tao Ye, Beijing Normal University, Beijing, China
 
Empirical Critical Levels of Ozone for U.S. Tree Species and Their Uncertainties with Machine Learning (1151040)
ShihYing Chang1, Nathan R Pavlovic2, Joey Huang1, Kenneth Craig1, Chris Clark3, Kevin A Thorn4 and Charles T Driscoll5, (1)Sonoma Technology, Inc., Petaluma, CA, United States, (2)Sonoma Technology, Inc., Petaluma, United States, (3)Environmental Protection Agency, Office of Research and Development, Washington, DC, United States, (4)U.S. Geological Survey, Denver, CO, United States, (5)Syracuse University, Department of Civil & Environmental Engineering, Syracuse, NY, United States
 
Reducing the Dimensionality of Time Series Using Singular Spectrum Analysis for Machine Learning Applications in Irrigation Management. (1160816)
Eduart Murcia Botache, University of Florida, Ft Walton Beach, FL, United States and Sandra Guzman, University of Florida, Ft Walton Beach, United States
 
AiBEDO: A hybrid AI model to capture the effects of cloud properties on global circulation and regional climate patterns (1166261)
Soo Kyung Kim1, Salva Ruhling Cachay1, Peetak Mitra1, Subhashis Hazarika1, Dipti Hingmire2, Haruki Hirasawa2, Philip J Rasch3, Hansi Alice Singh4 and Kalai Ramea5, (1)PARC, Palo Alto, United States, (2)University of Victoria, School of Earth and Ocean Sciences, Victoria, BC, Canada, (3)Pacific Northwest National Lab, Richland, WA, United States, (4)University of Victoria, Victoria, Canada, (5)PARC, Palo Alto, CA, United States
 
Early prediction of yield using high throughput phenotyping via UAS based images (1175027)
Sumantra Chatterjee1, Alper Adak1, Scott Wilde2, Regan Lindsay3, Colby Bass1, Seth Murray4 and Alper Adak, Scott Wilde, Regan Lindsay, Colby Bass, Seth Murray, (1)Texas A&M AgriLife Research, College Station, United States, (2)Texas A&M AgriLife Research (Former), College Station, United States, (3)Texas A&M AgriLife Research, College Station, TX, United States, (4)Texas A&M AgriLife and Research, College Station, United States
 
Forest structure analysis and above-ground biomass prediction in a European temperate forest via UAV-LiDAR, DL methods and spatial statistics. (1178380)
Jaime Caballer Revenga, University of Copenhagen, Department of Geosciences and Natural Resource Management, København K, Denmark, Stefan Oehmcke, University of Copenhagen, Department of Computer Science, Copenhagen, Denmark, Flurin Sutter, WSL Swiss Federal Institute for Forest, Snow and Landscape Research, Birmensdorf, Switzerland, Mana Gharun, ETH Zürich, Department of Environmental Systems Science, Zürich, Switzerland, Thomas Friborg, University of Copenhagen, Department of Geosciences and Natural Resource Management, København K, Denmark, Nina C Buchmann, ETH Zurich, Department of Environmental Systems Science, Zurich, Switzerland and Alexander Damm, University of Zurich, Department of Geography, Zurich, Switzerland
 
Global Sensitivity Analysis applied to a Land Surface Model Evaluated at an Evergreen Broad-leaf Forest Site. (1182749)
Raj Deepak S N1, Christian Seiler2 and Adam H Monahan1, (1)University of Victoria, Victoria, BC, Canada, (2)Environment and Climate Change Canada, Climate Processes Section, Victoria, BC, Canada
 
The Impact of Crop Rotation on Crop Attributes Detection Using Sentinel-1A Observations (1182919)
Mahya Ghazi Zadeh Hashemi1, Narendra N Das1,2 and Paul Siqueira3, (1)Michigan State University, Civil and Environmental Engineering, East Lansing, United States, (2)Michigan State University, Biosystem and Agricultural Engineering, East Lansing, United States, (3)University of Massachusetts Amherst, Electrical and Computer Engineering, Amherst, United States
 
Learning to Learn Ecological Processes in Tropical Forests (1191215)
Jiangong Liu1, Juan Nathaniel1, Wenli Zhao1, Weiwei Zhan1, Pierre Gentine2 and Xu Lian1, (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
 
Identifying the Relative Importance of Soil Moisture, Relative Humidity, and Temperature for Solar-Induced Chlorophyll Fluorescence of Crops Using Machine Learning Models (1199873)
Qiren Wang, Peking University, Beijing, China, Pierre Gentine, Columbia University, Department of Earth and Environmental Engineering, New York, NY, United States and Jiangong Liu, Columbia University, New York, United States
 
Exploiting Artificial Intelligence for Advancing Earth and Environmental System Science (Invited) (1200114)
Forrest M. Hoffman1, Jitendra Kumar2, Zheng Shi3, Elias Charbel Massoud4, Nathan Collier1 and Min Xu1, (1)Oak Ridge National Laboratory, Oak Ridge, United States, (2)Oak Ridge National Laboratory, Oak Ridge, TN, United States, (3)University of Oklahoma, Institute for Environmental Genomics, Department of Microbiology and Plant Biology, Norman, United States, (4)University of California Berkeley, Environmental Science, Policy, & Management, Berkeley, CA, United States
See more of: Biogeosciences
<< Previous Session Proposal | Next Session Proposal >>