H31K:
Applications of Machine Learning in Hydrology I

Submit an Abstract to this Session



Session ID#: 34833

Session Description:
An infusion of large datasets is transforming hydrologic sciences. Hydrologic data comes from satellites in space, meters in streams, wells in the subsurface, and many other sources. Unsupervised machine learning methods are able to extract signals from these datasets that are meaningful and difficult for humans to discern. Supervised machine learning methods can be trained on big datasets coming out of high-fidelity, computationally-intensive computer models to create fast and accurate reduced order models. This session seeks to bring together hydrologists who are applying machine learning methods to improve our understanding of hydrologic systems and enable modeling techniques outside of traditional numerical models.
Primary Convener:  Daniel O'Malley, Los Alamos National Laboratory, Computational Earth Sciences, Los Alamos, NM, United States
Convener:  Dr. Velimir monty V Vesselinov, Los Alamos National Laboratory, Computational Earth Sciences (EES-16), Los Alamos, NM, United States
Chairs:  Daniel O'Malley, Los Alamos National Laboratory, Computational Earth Sciences, Los Alamos, NM, United States and Dr. Velimir monty V Vesselinov, Los Alamos National Laboratory, Los Alamos, United States
OSPA Liaison:  Daniel O'Malley, Los Alamos National Laboratory, Computational Earth Sciences, Los Alamos, NM, United States
Index Terms:

1894 Instruments and techniques: modeling [HYDROLOGY]
1914 Data mining [INFORMATICS]
1916 Data and information discovery [INFORMATICS]
1942 Machine learning [INFORMATICS]

Abstracts Submitted to this Session:

Assessing the Ability of Vegetation Indices to Identify Shallow Subsurface Water Flow Pathways from Hyperspectral Imagery Using Machine Learning:  Methodology (278663)
Jefferson M Byers and Katarina Doctor, Naval Research Laboratory, Washington, DC, United States
Prediction of Baseflow Index of Catchments using Machine Learning Algorithms (241511)
Bidhyananda Yadav, University of Florida, Civil and Coastal Engineering, Ft Walton Beach, United States and Kirk Hatfield, University of Florida, Civil and Coastal Engineering, Gainesville, FL, United States
Machine learning to construct reduced-order models and scaling laws for reactive-transport applications (255346)
Maruti Kumar Mudunuru1, Satish Karra2 and Dr. Velimir monty V Vesselinov2, (1)Los Alamos National Laboratory, Los Alamos, NM, United States, (2)Los Alamos National Laboratory, Los Alamos, United States
An information-theoretic approach to upscaling of hydraulic properties (226966)
Francesca Boso, Stanford University, Stanford, CA, United States and Daniel M Tartakovsky, Stanford University, Energy Science and Engineering, Stanford, United States

See more of: Hydrology