U012
Machine Learning Applications in Earth, Energy, and Environmental Studies
Session ID#: 157919
Session Description:
Current trends in Earth, Energy & Environmental studies focus on the use of machine learning (ML) to inform problem-solution and decision-making. ML applications include data-driven ML (DDML), physics-informed ML (PIML), and multimodal machine learning (MML). In contrast to DDML and PIML, MML affords the possibility to incorporate any number of categorical and numeric (derived using numerical model calibrations/inversions, DDML, and/or PIML) features along with point field measurements to inform the assimilation, discovery, and prediction process. We seek case studies that use ML in their workflow to 1. Develop predictive understanding of the Earth system under changing environment, 2. Develop adaptive subsurface management strategies for energy production and storage, and waste isolation, or 3. Ensure water and ecosystem security under a changing environment. Successful ML applications will render informed policy and sustainable resource management.
Co-Sponsor(s):
Index Terms:
0999 General or miscellaneous [EXPLORATION GEOPHYSICS]
1942 Machine learning [INFORMATICS]
8199 General or miscellaneous [TECTONOPHYSICS]
Primary Convener: Michael J Friedel, University of Colorado Denver, Physics, Denver, CO, United States
Conveners: Gege Wen, Stanford University, Energy Resources Engineering, Stanford, CA, United States, Erin Wallin, HIGP/SOEST/Univ Hawaii, Honolulu, HI, United States and Sahar Bakhshian, Bureau of Economic Geology, University of Texas at Austin, Austin, TX, United States
AI-enabled Rapid Tsunami Forecasting for Prompt Evacuation (Invited) (1080861)
Fumiyasu Makinoshima1, Yusuke Oishi1, Takashi Yamazaki1, Takashi Furumura2 and Fumihiko Imamura3, (1)Fujitsu Limited, Kawasaki, Japan, (2)ERI, Univ. Tokyo, Bunkyo-Ku, Japan, (3)Tohoku University, International Research Institute of Disaster Science, Sendai, Japan
Machine Learning within the Cognitive Mission Manger for Wildland Fire Management (1097944)
Lora Koenig1, Anthony Nowicki2, Lynn Nicole Montgomery3, Daniel Lordan2 and The Cognitive Mission Manger Team, (1)Lockheed Martin Advanced Technology Center, Palo Alto, CA, United States, (2)Lockheed Martin Corporation, Arlington, United States, (3)Lockheed Martin Space, Boulder, United States
Adaptive physics-informed deep learning for the parameterization of orographic gravity waves (1108100)
Thi-Nguyen-Khoa Nguyen1, Christophe Millet2, Thibault Dairay3, Raphaël Meunier3 and Mathilde Mougeot4, (1)ENS Paris-Saclay, Gif-sur-Yvette, France, (2)CEA Commissariat à l'Energie Atomique DAM, Arpajon Cedex, France, (3)MICHELIN, Ladoux, France, (4)ENS Paris-Saclay, Gif, France
A Neural Differentiable Framework for Efficient Simulation and Rapid Optimization of Energy Harvesters (1125010)
Xiantao Fan1,2, Sisi Meng2,3 and Jianxun Wang1,4, (1)University of Notre Dame, Department of Aerospace and Mechanical Engineering, Notre Dame, United States, (2)University of Notre Dame, Environmental Change Initiative, Notre Dame, United States, (3)University of Notre Dame, Keough School of Global Affairs, Notre Dame, United States, (4)University of Notre Dame, Center for Sustainable Energy (ND Energy), Notre Dame, United States
Use machine learning to detect tectonic movement in seafloor pressure data for seismic and tsunami hazard assessment (Invited) (1149752)
Meng (Matt) Wei1, Bing He1, Xiaozhuo Wei1, Yang Shen1 and Marco Alvarez2, (1)University of Rhode Island, Graduate School of Oceanography, Narragansett, RI, United States, (2)University of Rhode Island, Kingston, RI, United States
Adaptive Multi-Modal AI/ML Tool for Predicting Subsurface Properties (1154862)
MacKenzie Mark-Moser, Kelly K Rose2, Patrick Wingo3, Scott Pantaleone4, Dakota Zaengle3, Jacob Shay4, Brendan Hoover3, Thomas Martin5 and Chukwuemeka Okoli6, (1)National Energy Technology Laboratory, Albany, OR, United States, (2)Leidos Research Support Team, Albany, OR, United States, (3)National Energy Technology Laboratory, Albany, United States, (4)National Energy Technology Laboratory, Golden, United States, (5)National Energy Technology Laboratory Support Staff, Albany, Oregon, United States
Prediction of Regional Soil Moisture Dynamics Using Deep Leaning Techniques (1174191)
Sahar Bakhshian1, Negar Zarepakzad2, Hannes Nevermann3, Cathy Hohenegger4, Dani Or5,6 and Nima Shokri3, (1)University of Texas at Austin, Austin, TX, United States, (2)Hamburg University of Technology, Hamburg, Germany, Institute of Geo-Hydroinformatics, Hamburg, Germany, (3)Hamburg University of Technology, Institute of Geo-Hydroinformatics, Hamburg, Germany, (4)Max Planck Institute for Meteorology, Hamburg, Germany, (5)Swiss Federal Institute of Technology ETH, Dept. of Environmental Syst. Sci., Zürich, Switzerland, (6)DRI Desert Research Institute, Division of Hydrologic Sciences, Reno, United States
Physics-constrained Machine Learning with Subsurface Codes (1187457)
Satish Karra, Pacific Northwest National Laboratory, Richland, WA, United States, Bulbul Ahmmed, Los Alamos National Laboratory, Los Alamos, NM, United States and Maruti K. Mudunuru, Pacific Northwest National Laboratory, Richland, United States
Imaging and Characterizing Small-Scale Fractures at the Soda Lake Geothermal Field Using Seismic Double-Beam Neural Network (DBNN) (Invited) (1189152)
Yingcai Zheng, University of Houston, Earth and Atmospherical Sciences Dept, Houston, TX, United States, Lianjie Huang, Los Alamos National Laboratory, Geophysics Group, Los Alamos, NM, United States and Trenton T Cladouhos, Cyrq Energy Inc., Salt Lake City, UT, United States
Physics-informed Gaussian process regression model for parameter estimation in groundwater models (Invited) (1059749)
Alexandre M Tartakovsky, University of Illinois at Urbana Champaign, Civil and Environmental Engineering, Champaign, United States, Yu-Hong Yeung, Pacific Northwest National Laboratory, Richland, United States and David A Barajas-Solano, Pacific Northwest National Laboratory, Richland, WA, United States
Forecasting Energy Consumption in Residential Buildings Using Machine Learning Models (1079981)
Hoang Minh Nguyen, National Taiwan University of Science and Technology, Taoyuan County, Taiwan, Dinh-Nhat Truong, University of Architecture Ho Chi Minh City, Ho Chi Minh City, Vietnam and Jui-Sheng Chou, National Taiwan University of Science and Technology, Taipei, Taiwan
