H086
Improving Agricultural Water and Soil Moisture Monitoring with Earth Observations and Machine Learning: Innovations in Data-Driven Approaches
Session ID#: 250039
Session Description:
Monitoring agricultural water use and soil moisture is essential for ensuring sustainable food production, improving irrigation efficiency, and responding to climate-driven water challenges. Recent advancements in Earth observations (EO) and Machine Learning (ML) are enabling more precise, timely, and scalable assessments of these critical parameters.This session invites contributions that leverage EO data such as satellite imagery, airborne sensing, and in situ networks, alongside ML techniques to enhance monitoring, modeling, and forecasting of agricultural water use and soil moisture dynamics. Key topics include: 1) Satellite-based soil moisture retrieval and validation (e.g., SMAP, Sentinel, Landsat), 2) Hybrid physics-ML modeling approaches for soil moisture estimation, 3) Monitoring evapotranspiration, irrigation, and agricultural water use, 4) Integration of EO, meteorological, and ground data using ML techniques, 5) Real-time and near-real-time monitoring, and Sub-Seasonal to Seasonal (S2S) forecasting systems for agricultural water management, 6) Case studies on applied monitoring for climate resilience and food security
Co-Sponsor(s):
Index Terms:
0402 Agricultural systems [BIOGEOSCIENCES]
1807 Climate impacts [HYDROLOGY]
1842 Irrigation [HYDROLOGY]
1866 Soil moisture [HYDROLOGY]
Primary Convener: Dr. Sushree Swagatika Swain, University of California San Diego, Scripps Institution of Oceanography, San Diego, United States
Conveners: Akash Koppa, University of Maryland College Park, Dept. of Environmental Science & Technology, Maryland, United States, Somnath Mondal, Northeastern University, Civil & Environmental Engineering, Boston, MA, United States and Dr. Ashutosh Sharma, PhD, Indian Institute of Technology Roorkee, Department of Hydrology, Roorkee, India
Student/Early Career Convener: Mr. Sudhanshu Kumar, Auburn University, Department of Crop, Soil & Environmental Sciences, Auburn, United States
Evaluation of Soil Moisture Products of SMAP, SMOS, and AMSR2 in a 50 km Study Area on the Mongolian Plateau (1857877)
Ichirow Kaihotsu, Hiroshima Univ, Higashihiroshima, Japan, Kentaro AIDA, Japan Aerospace Exploration Agency, Earth Observation Research Center, Tsukuba, Japan, Jun Asanuma, University of Tsukuba, Tsukuba, Japan and Nozomu Hirose, National Institute of Technology, Matsue College, Department of Civil Environmental Engineering, Matsue, Japan
Detecting Irrigation Signals from SMAP L3 and L4 Soil Moisture: A Case Study in California's Central Valley (1876969)
Xin Huang, The University of Tokyo, Department of Civil Engineering, Tokyo, Japan, Qing He, The University of Tokyo, Tokyo, Japan, Naota Hanasaki, National Institute for Environmental Studies (NIES), Center for Climate Change Adaptation, Tsukuba, Japan, Rolf H Reichle, NASA Goddard Space Flight Center, Greenbelt, United States and Taikan Oki, The University of Tokyo (UTokyo), Department of Civil Engineering, Tokyo, Japan
Analysis of the Impact of Soil Moisture Distribution on Microwave Radiometer Soil Moisture Products by AMSR2, SMAP, and SMOS in JAXA’s Validation Site, Mongolia (1877008)
Kentaro AIDA1, Misako Kachi1, Nozomu Hirose2, Jun Asanuma3, Ichirow Kaihotsu4 and Enkhbayar Batbayar5, (1)Japan Aerospace Exploration Agency, Earth Observation Research Center, Tsukuba, Japan, (2)National Institute of Technology, Matsue College, Department of Civil Environmental Engineering, Matsue, Japan, (3)University of Tsukuba, Tsukuba, Japan, (4)Hiroshima Univ, Higashihiroshima, Japan, (5)IRIMHE, Ulaanbaatar, Mongolia
Exploring the Heterogenous Nature of Irrigated Agricultural Fields using Remote Sensing Data (1889058)
Rahel Pommerenke1, Ryan Smith1, Jeffrey D Niemann1 and Neil Hansen2, (1)Colorado State University, Department of Civil and Environmental Engineering, Fort Collins, United States, (2)Brigham Young University, Provo, UT, United States
Investigating the Drivers of Site-Level Forest Soil Moisture Dynamics (1891952)
Jake Cohen1,2, Yushu Xia3, Jiaming Duan4 and Hancheng Guo2,5, (1)University of Toronto, Toronto, ON, Canada, (2)Lamont -Doherty Earth Observatory, Palisades, United States, (3)Columbia University of New York, NYC, United States, (4)Columbia University of New York, Lamont-Doherty Earth Observatory, Palisades, United States, (5)Zhejiang University, Hangzhou, China
Advancing Real-Time Soil Monitoring Through Machine Learning and Sensor Networks: The Missouri MoHIC Initiative (1896055)
Varshini Kumanan1, Zachary Leasor2, Michael Sunde2 and Bimal Gyawali3, (1)University of Missouri, Columbia, Missouri, UNITED STATES, (2)University of Missouri Columbia, Columbia, United States, (3)University of Missouri Columbia, School of Natural resources, Columbia, United States
Unveiling thriving small-scale irrigation in Sub-Saharan Africa using geospatial foundation models (1908811)
Anna Boser1, Jackson Coldiron2, Karena Lai3, Jasper Luo3, Madhav Rao3, Kathy Baylis4 and Kelly K Caylor5, (1)University of California Santa Barbara, Bren School of Environmental Science and Management, Santa Barbara, CA, United States, (2)University of California Santa Barbara, Bren School of Environmental Science and Management, Santa Barbara, United States, (3)University of California Santa Barbara, Santa Barbara, United States, (4)University of California Santa Barbara, Geography, Santa Barbara, United States, (5)University of California Santa Barbara, Department of Geography and Bren School of Environmental Science and Management, Santa Barbara, United States
Forecasting Soil Tension from Weather Data Using LSTM for Agricultural Water Monitoring (1919591)
Mahesh Maskey, University of California Davis, Land, Air and Water Resources, Davis, United States, Sumanta Chatterjee, University of Maryland College Park, Environmental Science and Technology, College Park, United States and Sumanta Chatterjee
A Contrastive Self-supervised Learning Model for Soil Moisture Retrieval from P-band PolSAR (1922807)
Sam Khallaghi, Clark University, Clark Center for Geospatial Analytics, Worcester, United States, Anke Fluhrer, German Aerospace Center DLR Oberpfaffenhofen, Microwaves and Radar Institute, Oberpfaffenhofen, Germany, Thomas Jagdhuber, Microwaves and Radar Institute, German Aerospace Center (DLR), Munich, Germany and Hamed Alemohammad, PhD, Clark University, Center for Geospatial Analytics, Worcester, United States
Identifying Optimal Timing and Sensor Integration for Predicting Soil Moisture and Electrical Conductivity using UAV Remote Sensing, Terrain, and Geophysics with ANN Models in Terraced Fields of the U.S. Midwest (1928866)
Effat Eskandari1, Katherine Grote1 and Joel Schott2, (1)Missouri University of Science and Technology, Earth Science and Engineering, Rolla, United States, (2)Missouri University of Science and Technology, Rolla, MO, United States
Automated Machine Learning Framework for Daily Soil Moisture Modeling Across Depths Using Remote Sensing and In Situ Observations (1939144)
Bimal Gyawali1, Michael Sunde2, Zachary Leasor2 and Varshini Kumanan3, (1)University of Missouri Columbia, School of Natural resources, Columbia, United States, (2)University of Missouri Columbia, Columbia, United States, (3)University of Missouri, Columbia, Missouri, UNITED STATES
Reducing Uncertainty in SMAP L4 Soil Moisture Retrievals through ANN-Based Modelling: Watershed-Scale Insights from Eastern India (1939552)
Akash Atnurkar1, Meenu Ramadas2 and Shanti Swarup Biswal1, (1)Indian Institute of Technology Bhubaneswar, School of Infrastructure, Bhubaneswar, India, (2)Indian Institute of Technology Bhubaneswar, Department of Civil Engineering, School of Infrastructure, Bhubaneswar, India
Calibrating a Python-Based Water Balance Model (pyWBM) with Machine Learning and Multi-Source Data (1940678)
Tahsina Alam, University of Illinois at Urbana-Champaign, Urbana, Illinois, UNITED STATES, David Lafferty, Scientist II, Boston, United States, Trent Ford, University of Illinois Urbana Champaign, Illinois State Water Survey, Champaign, United States and Ryan L Sriver, University of Illinois, Urbana, IL, United States
Multi-Temporal Machine Learning Approach for Assessing Groundwater-Agriculture Nexus Using Remote Sensing Indices and GRACE Data (1951961)
Iram Naz, Hong Fan and Rana Waqar Aslam, Wuhan University, China, State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan 430079, China., Wuhan, China
Soil moisture prediction with deep learning and machine learning in semi-arid cropping systems (1967251)
Rajan Ghimire, New Mexico State University Main Campus, Las Cruces, NM, United States, Prakriti Bista, New Mexico State University, Agricultural Science Center, Clovis, United States, Sarbagya Shakya, Eastern New Mexico University, Portales, United States and Olufemi Adebayo, New Mexico State University, Clovis, United States
ROOTS: A Harmonized Open-Source Global Soil Moisture Database for Drought and Hydroclimate Analysis (1969219)
Aandishah Samara, Columbia University of New York, Earth and Environmental Sciences, Palisades, NY, United States and Stephen Cropper, University of California, Los Angeles, Earth and Environmental Sciences Division, Los Angeles, United States
Optimizing Irrigation through a Novel Framework Combining Physical Processes with Model-Based Deep Reinforcement Learning (1972265)
Krishna Panthi, Clemson University, School of Computing, Clemson, SC, United States, Vidya Samadi, Clemson University, Department of Agricultural Sciences, Clemson, SC, United States and Carlos Toxtli, Clemson University, School of Computing, Clemson, United States
Early monitoring of rice distribution under climate variability using transfer learning, Random Forest, and spectral index time series in California (1981833)
Romina Díaz Gómez1, Marina Reyes Lopez Mautner1, Charles A. Young2 and Matthew Holland3, (1)Stockholm Environment Institute, US Water, Davis, CA, United States, (2)Stockholm Environment Institute, US Water, Davis, United States, (3)California State Water Resources Control Board, Bay-Delta Section, Sacramento, United States
Monitoring agricultural water use and linking crop evapotranspiration with yield (1995435)
Adam Schreiner-McGraw, USDA-ARS, Cropping Systems and Water Quality Research Unit, Columbia, United States, Martha Anderson, USDA ARS, Hydrology and Remote Sensing Laboratory, Beltsville, United States, Ken Sudduth, USDA-Agricultural Research Service, Columbia, MO, United States and Curtis Ransom, USDA-ARS, Columbia, United States
An AI-Based Dynamical System Framework for Early Warning of Flash Drought Onsets (Invited) (1847080)
Di Tian, Auburn University, Department of Crop, Soil & Environmental Sciences, Auburn, United States and Fang Wang, Auburn University, Crop, Soil and Environmental Sciences, Auburn, AL, United States
High Resolution SMAP Soil Moisture in Agriculture: Interactions Between Evapotranspiration, Precipitation, and Soil Moisture (1848941)
Annelise Turman, University of Virginia, Charlottesville, VA, United States, Bin Fang, University of Virginia, Civil and Environmental Engineering, Charlottesville, VA, United States, Ryan Smith, Colorado State University, Civil and Environmental Engineering, Fort Collins, United States, Venkataraman (Venkat) Lakshmi, University of Virginia, Civil and Environmental Engineering, Charlottesville, United States and Steve Blecker, Colorado State University, College of Agriculture Sciences, Fort Collins, United States
