H13B:
Big Data and Machine Learning in Hydrology and Subsurface Flow and Transport I


Submit an Abstract to this Session


Session ID#: 62367

Session Description:
We are witnessing tremendous advances in analysis of massive data streams, ultra-fast computing resources, physics-informed machine learning as well as significant increase in instrumentation density and quality. These advances present opportunities for novel methods to aid in both scientific discovery, data discovery, and predictive modeling. This session invites contributions describing applications of machine learning methods and “big” and “small” data problems for a) enhance decision making, b) producing new datasets, d) gaining new physical insights in hydrologic processes, e) investigating connections between water and other physical/human systems. The target applications include water resources management, subsurface reactive transport, CO2 sequestration and other related disciplines.
Primary Convener:  Alexandre M Tartakovsky, University of Illinois at Urbana Champaign, Civil and Environmental Engineering, Champaign, United States
Conveners:  Chaopeng Shen, Pennsylvania State University Main Campus, Department of Civil and Environmental Engineering, University Park, United States, Dr. Grey Stephen Nearing, PHD, Upstream Tech, Tuscaloosa, United States and Gowri Srinivasan, Los Alamos National Laboratory, Los Alamos, NM, United States
Primary Liaison:  Chaopeng Shen, Pennsylvania State University Main Campus, Department of Civil and Environmental Engineering, University Park, United States
Chairs:  Alexandre M Tartakovsky, University of Illinois at Urbana Champaign, Civil and Environmental Engineering, Champaign, United States, Chaopeng Shen, Pennsylvania State University Main Campus, Department of Civil and Environmental Engineering, University Park, United States, Dr. Grey Stephen Nearing, PHD, Upstream Tech, Tuscaloosa, United States and Gowri Srinivasan, Los Alamos National Laboratory, Los Alamos, NM, United States
OSPA Liaison:  Alexandre M Tartakovsky, University of Illinois at Urbana Champaign, Civil and Environmental Engineering, Champaign, United States

Cross-Listed:
  • IN - Earth and Space Science Informatics
Index Terms:

1869 Stochastic hydrology [HYDROLOGY]
1895 Instruments and techniques: monitoring [HYDROLOGY]
1914 Data mining [INFORMATICS]
1942 Machine learning [INFORMATICS]

Abstracts Submitted to this Session:

Predicting in shale resources: multi-phase flow & transport or data science? (Invited) (360619)
Jef Caers, Stanford University, Earth and Planetary Sciences, Stanford, United States
Uncertainty Quantification using Physics based Machine Learning and Data Classification (398787)
Gurpreet Singh, Austin, TX, United States and Mary Wheeler, University of Texas at Austin, Austin, TX, United States
Deep Convolutional Encoder-Decoder Networks for Uncertainty Quantification of Dynamic Multiphase Flow in Heterogeneous Media (408291)
Shaoxing Mo, Nanjing University, Nanjing, China and Nicholas Zabaras, University of Notre Dame, Center for Informatics and Computational Science, Notre Dame, IN, United States
Approximate Bayesian model inversion for PDEs with unknown parameters and constitutive relations (448922)
David A Barajas-Solano, Pacific Northwest National Laboratory, Richland, WA, United States and Alexandre M Tartakovsky, University of Illinois at Urbana Champaign, Civil and Environmental Engineering, Champaign, United States
Integration of Seismic and Flow-related Data for High-resolution Reservoir Imaging Using Bayesian Models and Conditional Generative Adversarial Networks (394488)
Jinsong Chen, Lawrence Berkeley National Laboratory, Berkeley, CA, United States, Michael Commer, Lawrence Berkeley National Lab, Berkeley, United States and Gary Michael Hoversten, Chevron Corporation Houston, Geophysical R&D, Houston, TX, United States
Do internals of neural networks make sense in the context of hydrology? (396081)
Frederik Kratzert1, Mathew Herrnegger2, Daniel Klotz3, Sepp Hochreiter1 and Günter Klambauer1, (1)Johannes Kepler University, Institute for Machine Learning, Linz, Austria, (2)BOKU University of Natural Resources and Life Sciences, Institute for Hydrology and Water Management, Vienna, Austria, (3)BOKU University of Natural Resources and Life Sciences, Institute of Water Management, Hydrology and Hydraulic Engineering, Vienna, Austria
Model Reduction of Flow Through Fractured Media Using Graph Theoretic and Machine Learning Approaches (420284)
Hari Selvi Viswanathan1, Jeffrey Hyman2, Satish Karra3, Daniel O'Malley1, Shriram Srinivasan3, Aric Hagberg3 and Gowri Srinivasan2, (1)Los Alamos National Laboratory, Earth and Environmental Sciences Division, Los Alamos, United States, (2)Los Alamos National Laboratory, Los Alamos, NM, United States, (3)Los Alamos National Laboratory, Los Alamos, United States
Information Theory of Multiscale Simulations and Data Assimilation (438749)
Francesca Boso, Stanford University, Energy Science Engineering, Stanford, United States, Hannah Lu, Stanford University, Energy Resources Engineering, Stanford, United States and Daniel M Tartakovsky, Stanford University, Energy Science and Engineering, Stanford, United States

See more of: Hydrology