H21H:
Prediction of Hydrologic Behavior from Sparse Information Using Statistical and Machine Learning Techniques I Posters

Submit an Abstract to this Session



Session ID#: 27468

Session Description:
Recent years have seen the development of a variety of techniques for modeling flow and transport behavior which exhibit better fidelity to observational data than classical models. One limitation of such techniques has been the difficulty of using them in a predictive context by constraining their parameters a priori. The recent flourishing of development in machine learning techniques and high-performance computing promises change this situation, and allow for the discovery of predictive relationships relating hydrologic observables to quantities of interest. Such techniques also make it possible to derive empirically-grounded error envelopes for predictions. With this motivation, the session aims to highlight recent theoretical and technical advances in predictive flow and (reactive) transport modeling, as well as error analysis, throughout the hydrologic sciences. These include advances may include approaches employing innovative machine learning techniques, as well as those employing classic statistical regression, Bayesian, and other approaches.
Primary Convener:  Scott K Hansen, Los Alamos National Laboratory, Computational Earth Sciences (EES-16), Los Alamos, NM, United States
Conveners:  Yashar Mehmani, Stanford University, Energy Resources Engineering, Stanford, CA, United States and Maruti Mudunuru, Los Alamos National Laboratory, Los Alamos, NM, United States
Chairs:  Scott K Hansen1, Yashar Mehmani2 and Maruti Mudunuru1, (1)Los Alamos National Laboratory, Los Alamos, NM, United States(2)Stanford University, Energy Resources Engineering, Stanford, CA, United States
OSPA Liaison:  Scott K Hansen, Los Alamos National Laboratory, Los Alamos, NM, United States
Index Terms:

1816 Estimation and forecasting [HYDROLOGY]
1869 Stochastic hydrology [HYDROLOGY]
1873 Uncertainty assessment [HYDROLOGY]
1942 Machine learning [INFORMATICS]

Abstracts Submitted to this Session:

Winter precipitation forecast in the European and Mediterranean regions using cluster analysis (218482)
Sonja Molnos, Potsdam Institute for Climate Impact Research, Potsdam, Germany
Revealing the Hidden Water Budget of an Alpine Volcanic Watershed Using a Bayesian Mixing Model (236333)
Katherine H. Markovich, University of California Davis, Davis, United States, Jose Luis Arumi, Universidad de Concepcion, Water Resources, Chillan, Chile, Helen E Dahlke, University of California Davis, Land, Air and Water Resources, Davis, CA, United States and Graham E Fogg, Univ California Davis, Davis, United States
A hierarchical spatial model for well yield in complex aquifers (243269)
Justin Montgomery and Francis O'sullivan, Massachusetts Institute of Technology, Cambridge, MA, United States
Predicting hydrologic function with the streamwater mircobiome (245921)
Stephen P Good, Oregon State University, Biological and Ecological Engineering, Corvallis, OR, United States, Dawn URycki, Oregon State University, Department of Biological & Ecological Engineering, Corvallis, United States and Byron C Crump, Oregon State University, College of Earth, Ocean, and Atmospheric Science, Corvallis, United States
Predicting Upscaled Behavior of Aqueous Reactants in Heterogeneous Porous Media (266998)
Elise E Wright1, Scott K Hansen2, Diogo Bolster1, David H Richter3 and Dr. Velimir monty V Vesselinov4, (1)University of Notre Dame, Notre Dame, IN, United States, (2)Los Alamos National Laboratory, Los Alamos, NM, United States, (3)University of Notre Dame, Department of Civil & Environmental Engineering & Earth Sciences, Notre Dame, United States, (4)Los Alamos National Laboratory, Los Alamos, United States

See more of: Hydrology