Novel Data- and Machine Learning-Driven Approaches to Seismogenesis and Engineering Seismology
Session ID#: 157061
Session Description:
The goal of this “Innovation” session is to share novel data- and machine learning-driven approaches to the seismogenesis (i.e., science of causality and processes of earthquakes) and engineering seismology with a wide range of researchers in geophysics, data and computer science, natural hazard engineering, and diverse stakeholders. This Innovation session will cover recent advances in a variety of research activities that leverage novel methods of data science and machine learning, adding a new dimension to the study of monitoring earthquake behaviors, earthquakes forecasting, extreme earthquake prediction, hazard mitigation engineering, seismic loss estimation, and so on. This Innovation session will cover how new technologies of data and machine learning positively innovate the existing research paradigms and the newly emerging research ideas in the seismogenesis and engineering seismology areas. This Innovation session is intrinsically multi-disciplinary and seeks to forge mutually beneficial synergy through this intellectual exchange with broad audiences. In view of the current global pandemic circumstances, this Innovation session will adopt a hybrid presentation format – a combination of in-person on-site presentations and pre-recorded presentations of the co-conveners and selected presenters worldwide. A 90-minute session is expected.
Primary Convener: In Ho Cho, Associate Professor, Iowa State University, Civil, Construction, and Environmental Engineering, Ames, United States
Conveners: Haeyoung Noh, Stanford University, Civil and Environmental Engineering, Stanford, United States, Keith Porter, University of Colorado at Boulder, Boulder, CO, United States and Surendra Somala, Indian Institute of Technology, Hyderabad, Civil Engineering, Sangareddy , Telangana, India
Random Forest modification for multivariate categorical data imputation (1169337)
Jaekwang Kim, Professor, Iowa State University, Statistics, Ames, United States, Yonghyun Kwon, Iowa State University, Statistics, Ames, United States and Sayantani Ghosh, Iowa State University, Computer Science, Ames, United States
From Strong Motion to InSAR: Efficient Generation of Large Magnitude Synthetic Data for Machine Learning Applications (Invited) (1176994)
Diego Melgar, University of Oregon, Department of Earth Sciences, Eugene, OR, United States, Ivan Rodero, EMSO ERIC, CMO, Rome, Italy, Jiun-Ting Lin, Institute of Earth Sciences Academia Sinica, Taipei, Taiwan, Marcus Adair, University of Utah, Salt Lake City, United States, Sydney Dybing, Washington University in St Louis, St. Louis, MO, United States, David Small, University of Oregon, Eugene, OR, United States, Tara Nye, University of Oregon, Earth Sciences, Eugene, OR, United States, Oluwaseun Idowu Fadugba, Boston College, Chestnut Hill, MA, United States, Amanda M Thomas, University of Oregon, Department of Earth Sciences, Eugene, United States and Valerie J Sahakian, UC San Diego SIO, La Jolla, United States
Size Effects in Fault Dynamics (Invited) (1062720)
Ahmed E Elbanna, University of Illinois at Urbana Champaign, Department of Civil and Environmental Engineering, Urbana, IL, United States, Napat Tainpakdipat, University of Illinois Urbana Champaign, Urbana, United States and Thomas H Heaton, California Institute of Technology, Division of Engineering and Applied Science, Pasadena, CA, United States
Seismic COmputational Platform for Empowering Discovery (SCOPED), Year 1: Collaboration, Software, Training, and Workshops (Invited) (1081915)
Carl Tape, University of Alaska Fairbanks, Geophysical Institute, Fairbanks, AK, United States, Ebru Bozdag, Colorado School of Mines, Golden, CO, United States, Marine Denolle, University of Washington, Department of Earth and Space Sciences, Seattle, United States, Felix Waldhauser, Columbia University, Lamont-Doherty Earth Observatory, Palisades, United States and Yinzhi Wang, University of Texas at Austin, Texas Advanced Computing Center, Austin, TX, United States
Gauss curvature-based new feature generation for data-driven prediction of extreme large earthquakes (Invited) (1058010)
Ashish Chapagain, Graduate Research Assistant, Iowa State University, Civil, Construction, and Environmental Engineering, Ames, United States and In Ho Cho, Associate Professor, Iowa State University, Civil, Construction, and Environmental Engineering, Ames, United States
Ultra Data-Oriented Parallel Fractional Hot Deck Imputation to Cure Missing Data of Earthquake Catalog (Invited) (1054179)
Yicheng Yang1, Ashish Chapagain1, Jaekwang Kim2 and In Ho Cho3, (1)Graduate Research Assistant, Iowa State University, Civil, Construction, and Environmental Engineering, Ames, United States, (2)Professor, Iowa State University, Statistics, Ames, United States, (3)Associate Professor, Iowa State University, Civil, Construction, and Environmental Engineering, Ames, United States
