H037
Advancing Water Science Through Artificial Intelligence: Lessons, Strategies, and New Frontiers
Session ID#: 248844
Session Description:
Artificial intelligence (AI) is rapidly transforming our ability to understand, predict, and manage water resources. Recent advances in machine learning, deep learning, and hybrid modeling approaches have shown exceptional promise in capturing complex spatiotemporal dynamics. As these tools increasingly transition from research to real-world applications, the water community faces critical questions: What challenges arise when deploying AI tools in operational settings? How can AI contribute to new scientific discoveries? What are the next frontiers? This session invites critical reflections and practical insights into what works, what doesn’t, and why. We welcome contributions from hydrologists, environmental scientists, and AI researchers on topics including: model training and operational deployment, integrating domain knowledge into AI, quantifying model trustworthiness, and AI-driven scientific discovery. We are especially interested in frontiers such as foundation models and multimodal models that integrate sensor, text, and image data for comprehensive prediction and reasoning in water systems.
Index Terms:
0470 Nutrients and nutrient cycling [BIOGEOSCIENCES]
1816 Estimation and forecasting [HYDROLOGY]
1847 Modeling [HYDROLOGY]
1860 Streamflow [HYDROLOGY]
Primary Convener: Xiaofeng Liu, PhD, University of Michigan Ann Arbor, Michigan Institute for Data and AI in Society, Ann Arbor, MI, United States
Conveners: William S. Currie, University of Michigan, School for Environment and Sustainability, Ann Arbor, MI, United States, Tiantian Yang, University of Oklahoma Norman Campus, School of Civil Engineering and Environmental Science, Norman, United States and Yi Hong, Cooperative Institute for Great Lakes Research, University of Michigan, Ann Arbor, United States
Student/Early Career Convener: Alyssa Schubert, University of Michigan Ann Arbor, Ann Arbor, MI, United States
Improved Water Quality Prediction Using a Foundation Model (1852559)
Xiaofeng Liu, PhD, University of Michigan Ann Arbor, Michigan Institute for Data and AI in Society, Ann Arbor, MI, United States, Xiaobo Xia, National University of Singapore, School of Computing, Singapore, Singapore, Mohna Chakraborty, University of Michigan, Michigan Institute for Data and AI in Society, Ann Arbor, United States, Kuai Fang, Stanford University, Earth System Sciences, Stanford, United States, William S. Currie, University of Michigan, School for Environment and Sustainability, Ann Arbor, MI, United States, Samet Oymak, University of Michigan, Department of Electrical Engineering and Computer Science, Michigan, United States and Team of WQ foundation models
Toward Scientific Foundation Models for Aquatic Ecosystems (Invited) (1855085)
Abhilash Neog1, Medha Sawhney1, Kazi Sajeed Mehrab1, Sepideh Fatemi1, Mary E Lofton2, Amartya Dutta1, Aanish Pradhan1, Bennett J. McAfee3, Emma Marchisin3, Robert Ladwig4, Arka Daw5, Cayelan Carey2, Paul C Hanson6 and Anuj Karpatne7, (1)Virginia Polytechnic Institute and State University, Computer Science, Blacksburg, United States, (2)Virginia Polytechnic Institute and State University, Biological Sciences, Blacksburg, United States, (3)University of Wisconsin Madison, Madison, United States, (4)Aarhus University, Department of Ecoscience, Aarhus C, Denmark, (5)Oak Ridge National Lab, Oak Ridge, United States, (6)University of Wisconsin Madison, Center for Limnology, Madison, WI, United States, (7)Virginia Polytechnic Institute and State University, Computer Science, Blacksburg, VA, United States
Identifying trustworthiness challenges in deep learning models for continental-scale water quality prediction (1859615)
Xiaobo Xia, National University of Singapore, School of Computing, Singapore, Singapore, Xiaofeng Liu, PhD, Georgia Institute of Technology Main Campus, Georgia Water Resources Institute, Georgia Tech, School of Civil and Environmental Engineering, Atlanta, United States, Jiale Liu, The Pennsylvania State University, University Park, United States, Kuai Fang, Standford University, Standford, United States, Lu Lu, Yale University, New Heaven, United States, Samet Oymak, University of Michigan, Department of Electrical Engineering and Computer Science, Michigan, United States, William S. Currie, University of Michigan, School for Environment and Sustainability, Ann Arbor, MI, United States and Tongliang Liu, University of Sydney, Sydney, Australia
Assessment of Urban River Water Quality in Dhaka, Bangladesh Using Geographic Information System (GIS) and Machine Learning (ML) (1861844)
Md. Hasan, Asma Ul Husna, Md. Sojib Sheikh, Md Tafhimul Hasan, Jobayer Hossain, Tanvir Ahmed Khan, G.M. Rahad and Md Hasibul Islam, IUBAT—International University of Business Agriculture and Technology, Dhaka, Bangladesh, Department of Civil Engineering, College of Engineering and Technology, Dhaka, Bangladesh
River Stage Detection using Machine Learning and Image Segmentation for Flood Monitoring (1865486)
Dr. Derek Loftis, Virginia Institute of Marine Science, Gloucester Point, VA, United States, Varshin Bhaskaran, Syracuse University, Syracuse, United States, Sridhar Katragadda, City of Virginia Beach, Virginia Beach, United States and R Russell Lotspeich, USGS Water Mission Area, Hydrologic Networks Branch, Richmond, VA, United States
Using Entity-Aware LSTM to Enhance Streamflow Predictions in Transboundary and Large Lake Basins (1873352)
Yunsu Park, University of Michigan Ann Arbor, Ann Arbor, MI, United States, Xiaofeng Liu, PhD, Georgia Institute of Technology Main Campus, Georgia Water Resources Institute, Georgia Tech, School of Civil and Environmental Engineering, Atlanta, United States, Yuyue Zhu, University of Michigan, Ann Arbor, United States and Lauren M Fry, NOAA Great Lakes Environmental Research Laboratory, Ann Arbor, United States
From Predictions to Patterns with AI: A Differentiable SPARROW Framework for Improved Water Quality Prediction and Attribution (1882078)
Qianyu Zhao1, Bin Peng1, Zewei Ma1, Chaopeng Shen2, Ming Pan3, Jie Yang1, Dr. Mengqi Jia1, Kejie Zhao4, Puyang Zhao5, Jiaying Zhang4, Zhixian Lin4, Xiaocui Wu4, Qu Zhou4, Yuanxin Song1 and Kaiyu Guan4, (1)University of Illinois Urbana-Champaign, Urbana, United States, (2)Pennsylvania State University Main Campus, Department of Civil and Environmental Engineering, University Park, United States, (3)Center for Western Weather and Water Extremes (CW3E), Scripps Institution of Oceanography, University of California San Diego, La Jolla, United States, (4)University of Illinois Urbana-Champaign, Agroecosystem Sustainability Center, Institute for Sustainability, Energy, and Environment, Urbana, United States, (5)The University of Texas Health Science Center at Houston, Biostatistics and Data Science, Houston, United States
Text-Enhanced Hydrological Forecasting: Embedding Vectors for Improved Watershed Characterization (1888403)
Shuolong Xu1, Wenyu Ouyang2, Yikai Chai2 and Haoran Ma2, (1)Dalian University of Technology, School of Computer Science and Technology, Dalian, China, (2)Dalian University of Technology, School of Infrastructure Engineering, Dalian, China
A Deep State Space Model for Daily Reservoir Release Simulation Over the CONUS (1933681)
Jiaorui Zhang1, Milad Basirifard1, Jie Cao2 and Tiantian Yang1, (1)University of Oklahoma Norman Campus, School of Civil Engineering and Environmental Science, Norman, United States, (2)University of Oklahoma Norman Campus, School of Computer Science, Norman, United States
Adversarial Robustness and Internal Linearity of LSTM Rainfall–Runoff Models (1937462)
Yang Yang1,2, Joseph Janssen3, Majid Bayati4, Hoshin Gupta5 and Ting Fong May Chui1, (1)The University of Hong Kong, Department of Civil Engineering, Hong Kong SAR, China, (2)University of Massachusetts Boston, School for the Environment, Boston, United States, (3)University of British Columbia, Department of Earth, Ocean and Atmospheric Sciences, Vancouver, BC, Canada, (4)University of British Columbia, Department of Earth, Ocean and Atmospheric Sciences, Vancouver, Canada, (5)Hydrology and Atmospheric Sciences, The University of Arizona, Tucson, United States
Comparative Analysis of ML and DL Models for Reservoir Outflow Prediction: Hyperparameter Tuning and Feature Selection Across 441 CONUS Dams (1939796)
Milad Basirifard1, Jiaorui Zhang1, Jie Cao2 and Tiantian Yang1, (1)University of Oklahoma Norman Campus, School of Civil Engineering and Environmental Science, Norman, United States, (2)University of Oklahoma Norman Campus, School of Computer Science, Norman, United States
The response of Coreius guichenoti early resources in the lower Jinsha River to the variation of environmental characteristics (1944296)
Rui HAN, China Institute of Water Resources and Hydropower Research,State Key Laboratory of Water Cycle and Water Security, Beijing, China, Hongyi Yang, China Institute of Water Resources and Hydropower Research, State Key Laboratory of Water Cycle and Water Security, Beijing, China and Li Zeng, China Institute of Water Resources and Hydropower Research, State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, Beijing, China
Advancing Streamflow Prediction in Ungauged Basins of the Great Lakes Region Using LSTM (1951766)
Matthew Parent1, Dani Jones2, Lauren M Fry3 and Yi Hong2, (1)University of Michigan Ann Arbor, Ann Arbor, United States, (2)Cooperative Institute for Great Lakes Research, University of Michigan, Ann Arbor, United States, (3)NOAA Great Lakes Environmental Research Laboratory, Ann Arbor, United States
Evaluating Hybrid Models for Sediment Yield Prediction and Watershed Process Understanding (1965222)
Tsige Atilaw1,2, Yiluan Song3, Seth Temple2, Jamila Taaki2, Haotian Chen2 and Xiaofeng Liu, PhD4, (1)University of Michigan Ann Arbor, Climate and Space Sciences and Engineering, Ann Arbor, MI, United States, (2)University of Michigan Ann Arbor, Michigan Institute for Data and AI in Society, Ann Arbor, United States, (3)University of Michigan Ann Arbor, School for Environment and Sustainability, Institute for Global Change Biology, Michigan Institute for Data and AI in Society, Ann Arbor, United States, (4)University of Michigan Ann Arbor, Michigan Institute for Data and AI in Society, Ann Arbor, MI, United States
Neural Networks Think like Geomorphologists (1977151)
Jo jO.martin@coloradO.edu, University of Colorado Boulder, Department of Geological Sciences, Boulder, United States and Gregory E Tucker, University of Colorado at Boulder, Department of Geological Sciences and CIRES, Boulder, United States
Evaluating LSTM Model Adaptability to Input Perturbations (1992005)
Tasfia Tasnim, University of Massachusetts Amherst, Department of Civil and Environmental Engineering, Amherst, MA, United States and Konstantinos Andreadis, University of Massachusetts Amherst, Civil & Environmental Engineering, Amherst, United States
Accelerating Continental-Scale Differentiable Modeling with Sensitivity-Constrained AI Surrogates (2003516)
Leo Lonzarich1, Abdolmehdi Behroozi2, Doaa Aboelyazeed2, Daniel Kifer3 and Chaopeng Shen1, (1)Pennsylvania State University Main Campus, Department of Civil and Environmental Engineering, University Park, United States, (2)Pennsylvania State University Main Campus, Department of Civil and Environmental Engineering, University Park, PA, United States, (3)Pennsylvania State University, Department of Computer Science & Engineering, University Park, United States
