H009
Advances in Machine Learning Methods for Modeling Complex Subsurface Processes
Session ID#: 162095
Session Description:
This session will focus on recent advances in machine learning methods for a wide range of applications, including groundwater/surface-water interactions, groundwater flow, transport of contaminants, geothermal energy production, CO2 sequestration, waste disposal, and nuclear nonproliferation. We invite contributions describing ML methods that utilize experimental, field, and simulated data, and constraints in the form of physics laws. The potential applications could be data rich or data poor. Therefore, this session is interested in the advances demonstrating (1) the applications of ML methods for data-driven modeling that utilize massive data sets and could require data reduction and scalable algorithms, and (2) the applications of ML methods to problems where measurements are sparse, indirect, and/or only available at the scales different from the scale of interest. Therefore, we welcome contributions demonstrating scalable ML methods trained on massive data sets, physics-informed ML models, hybrid numerical- ML models, and ML-based surrogate models.
Index Terms:
1829 Groundwater hydrology [HYDROLOGY]
1830 Groundwater/surface water interaction [HYDROLOGY]
1832 Groundwater transport [HYDROLOGY]
1847 Modeling [HYDROLOGY]
Primary Convener: Alexandre M Tartakovsky, University of Illinois at Urbana Champaign, Civil and Environmental Engineering, Champaign, United States
Conveners: Pania Newell, University of Utah, Department of Mechanical Engineering, Salt Lake City, UT, United States and Hari Selvi Viswanathan, Los Alamos National Laboratory, Los Alamos, NM, United States
Groundwater level simulations using wavelet transform-assisted deep learning models. (1051337)
Sivarama Krishna Reddy Chidepudi, Mont Saint Aignan, FRANCE, Nicolas Massei, University of Rouen-Normandy, Continental and Coastal Morphodynamics Laboratory, Mont Saint Aignan, France, Abderrahim Jardani, Université de Rouen, Morphodynamique Continentale et Côtière,, Rouen, France, Abel Henriot, Bureau de Recherches Géologiques et Minières, Orleans, France, Delphine Allier, BRGM, Orleans, France and Lisa Baulon, Normandie Univ, UNIROUEN, UNICAEN, CNRS, M2C, Rouen, France
Efficient Design of Warm-VAPEX using a Neural Network Coupled with a Multi-objective Optimization Algorithm for an Oilsands Reservoir in Alberta, Canada (1053784)
Seoyoon Kwon1, Minsoo Ji1, Min Kim2, Juliana Leung3 and Baehyun MIN4, (1)Ewha Womans University, Department of Climate and Energy Systems Engineering, Seoul, Korea, Republic of (South), (2)Ewha Womans University, Severe Storm Research Center, Seoul, Korea, Republic of (South), (3)University of Alberta, Department of Civil & Environmental Engineering, Edmonton, Canada, (4)Ewha Womans University, Department of Climate and Energy Systems Engineering, Seoul, South Korea
Incorporating domain knowledge in estimating subsurface permeability using machine learning methods (Invited) (1064554)
Xingyuan Chen1, Peishi Jiang1, Pin Shuai1, Maruti K. Mudunuru2 and Alexander Y Sun3, (1)Pacific Northwest National Laboratory, Richland, WA, United States, (2)Pacific Northwest National Laboratory, Richland, United States, (3)University of Texas at Austin, Austin, TX, United States
Impacts of Climate Change on Spatial and Temporal Variability of Groundwater Nitrate in the Continental United States (1075123)
Chuyang Liu1, Austin Lord2, Shannon Bartelt-Hunt1 and Yusong Li3, (1)University of Nebraska Lincoln, Civil and Environmental Engineering, Lincoln, NE, United States, (2)Swarthmore College, Department of Engineering, Swarthmore, PA, United States, (3)University of Nebraska-Lincoln, Civil Engineering, Lincoln, NE, United States
Physics-Informed Neural Network Method for Parabolic Differential Equations with Sharply Perturbed Initial Conditions (1090198)
Yifei Zong, University of Illinois at Urbana Champaign, Civil and Environmental Engineering, Urbana, United States, Alexandre M Tartakovsky, University of Illinois at Urbana Champaign, Civil and Environmental Engineering, Champaign, United States and Qizhi He, University of Minnesota, Minneapolis, United States
Applied Machine Learning QSPR Model of Aromatic Hydrocarbon Solute Transport in Sandstone with XGBoost (1097931)
William James Blanford, CUNY Queens College, Flushing, NY, United States, Kennly Weerasinghe, CUNY Queens College, School of Earth and Environmental Sciences, Flushing, United States, Adam D Kapelner, CUNY Queens College, Mathematics, Flushing, NY, United States and Hubert B Majewski, CUNY Queens College, Mathematics, Flushing, United States
GANSim-surrogate: A combined framework for conditional geomodelling of subsurface reservoirs (1102253)
Suihong Song, Pengcheng Laboratory, Shenzhen, China, Dongxiao Zhang, South University of Science and Technology, Shenzhen, China, Tapan Mukerji, Stanford University, Department of Energy Resources Engineering; Department of Geological Sciences; Department of Geophysics, Stanford, United States and Nanzhe Wang, Peking University, Beijing, China
Long Short-Term Memory Networks to Explore the Spatiotemporal Evolution of Surface and Subsurface Water Sources in Alabama State (1118451)
Hossein Gholizadeh1, Yong Zhang2 and Jonathan M Frame2, (1)University of Alabama, Geological Sciences, Tuscaloosa, AL, United States, (2)University of Alabama, Geological Sciences, Tuscaloosa, United States
Machine Learning-Driven Temporal Downscaling of Groundwater Recharge Estimates to Obtain Event-Based Response (1124512)
Ali Ghaseminejad1, Nagaraj Bhat2, Pushpendra Raghav1, Mukesh Kumar3 and Prabhakar Clement3, (1)University of Alabama, Tuscaloosa, AL, United States, (2)Shri Madhwa Vadiraja Institute of Technology and Management, Computer science & Engineering, UDUPI, India, (3)University of Alabama, Department of Civil, Construction, and Environmental Engineering, Tuscaloosa, AL, United States
Reconstructing gap-filled groundwater level database for defective observational wells in the Irrigated Indus Basin (1137228)
Arfan Arshad1,2, Ali Mirchi1, Javier Vilcaez3 and Muhammad Umar Akbar4, (1)Oklahoma State University, Biosystems and Agricultural Engineering, Stillwater, United States, (2)University of Agriculture Faisalabad, Department of Irrigation and Drainage, Faculty of Agricultural Engineering and Technology, Faisalabad, Pakistan, (3)Oklahoma State University Main Campus, Boone Pickens School of Geology, Stillwater, OK, United States, (4)Oklahoma State University, Department of Biosystems and Agricultural Engineering, Stillwater, United States
Wavelet Denoising of GNSS Time Series Through Machine Learning. Application to the Campi Flegrei Caldera (1155260)
Rolando Carbonari, Hebrew University of Jerusalem, Jerusalem, Israel, Umberto Riccardi, The University of Naples Federico II, Naples, Italy, Prospero De Martino, National Institute of Geophysics and Vol, Napoli, Italy, Gianpaolo Cecere, Istituto Nazionale di Geofisica e Vulcanologia, Rome, Italy and Rosa Di Maio, University of Naples Federico II, Naples, Italy
