H023
Advancing watershed science using machine learning, diverse data, and mechanistic modeling

Session ID#: 83085

Session Description:
An understanding of watershed function that is both predictive and mechanistic is required to protect freshwater resources and quantify effects of climate change and extreme weather on the downstream delivery of water, nutrients, carbon, and metals – all of which affect water quality. To understand watershed functions, next-generation mechanistic models are needed, and they require diverse data, including hydrobiogeochemical observations and remote sensing. Integration of multi-modal, multi-scale data and models poses a significant challenge for advancing understanding. Here we invite theoretical and data-driven contributions that can advance the predictive understanding of watershed function. In particular (1) approaches that can aggregate a wide variety of data sources, including machine learning based techniques (2) algorithms that can quantify, and ideally minimize the uncertainty associated with data that is used to fit or initialize watershed-scale models, and (3) computational learning techniques to account for data challenges inherent in watershed-scale models.
Index Terms:

1805 Computational hydrology [HYDROLOGY]
1807 Climate impacts [HYDROLOGY]
1855 Remote sensing [HYDROLOGY]
1879 Watershed [HYDROLOGY]

Primary Convener:  Utkarsh Mital, Lawrence Berkeley National Laboratory, Berkeley, CA, United States
Conveners:  Dipankar Dwivedi, Lawrence Berkeley National Laboratory, Berkeley, CA, United States, James Bentley Brown, Lawrence Berkeley National Laboratory, Environmental Genomics and Systems Biology, Berkeley, CA, United States and Carl I Steefel, Lawrence Berkeley National Laboratory, Earth and Environmental Sciences, Berkeley, CA, United States
Primary Liaison:  Dipankar Dwivedi, Lawrence Berkeley National Laboratory, Berkeley, CA, United States
 
Transforming Earth Science by Bridging Machine Learning & Physics (Invited) (486407)
Hoshin Vijai Gupta, University of Arizona, Department of Hydrology and Atmospheric Sciences, Tucson, AZ, United States
 
Predicting Daily Groundwater Levels with Deep Learning Models (494270)
Reetik Sahu1, Juliane Müller2, Jangho Park2, Charuleka Varadharajan3, Bhavna Arora4, Boris Faybishenko3 and Deb Agarwal5, (1)Lawrence Berkeley National Laboratory, Computational Sciences Area, Berkeley, United States, (2)Lawrence Berkeley National Laboratory, Center for Computational Science and Engineering, Berkeley, CA, United States, (3)Lawrence Berkeley National Laboratory, Berkeley, CA, United States, (4)Lawrence Berkeley National Laboratory, Energy Geosciences Division, Berkeley, CA, United States, (5)LBNL, Berkeley, CA, United States
 
Application of artificial neural network to spatially assess the health risk from arsenic exposure via drinking groundwater in Lanyang plain (495818)
Chi-Chien Sun, Zhongli District, Taiwan, Taiwan, Jui-Sheng Chen, National Central University, Taoyuan City, Taiwan and Ching-ping Liang, Fooyin University, Kaohsiung City, Taiwan
 
Urban Stormwater Signatures Across the United States: A Machine Learning Approach (496789)
Celina Balderas Guzman, University of California Berkeley, Berkeley, CA, United States, Runzi Wang, Michigan State University, East Lansing, MI, United States, Oliver Muellerklein, University of California Berkeley, Berkeley, United States, Caitlin G Eger, Syracuse University, Syracuse, NY, United States and Matthew Smith, Florida International University, Miami, FL, United States
 
Hybrid Predictive Model: A hybrid deep learning and physically based model approach for large scale and long term estimation of water and carbon fluxes (499221)
Jiancong Chen1, Baptiste Dafflon2, Anh Phuong Tran3, Susan Hubbard2 and Yoram Rubin1, (1)University of California Berkeley, Berkeley, CA, United States, (2)Lawrence Berkeley National Laboratory, Earth and Environmental Sciences, Berkeley, CA, United States, (3)Lawrence Berkeley National Laboratory, Berkeley, CA, United States
 
Understanding the Dynamic Nature of Catchment Response Time through Large-Scale Machine Learning Analysis (503588)
Mistaya Langridge, University of Guelph, Harriston, ON, Canada, Bahram Gharabaghi, University of Guelph, School of Engineering, Guelph, ON, Canada and Hossein Bonakdari, University of Guelph, Guelph, ON, Canada
 
Using Information Flow for Whole System Understanding from Component Dynamics (518357)
Peishi Jiang1,2, Praveen Kumar3, Xingyuan Chen2 and Pin Shuai2, (1)University of Illinois at Urbana Champaign, Urbana, IL, United States, (2)Pacific Northwest National Laboratory, Richland, WA, United States, (3)University of Illinois at Urbana Champaign, Department of Civil and Environmental Engineering, Urbana, IL, United States
 
Multi-scale Watershed Modelling: From Point-scale to Basin-scale using Surrogate Models and Data Assimilation (522852)
Anjuli Jain Figueroa1,2 and Dennis McLaughlin2, (1)Stanford University, Stanford, CA, United States, (2)Massachusetts Institute of Technology, Cambridge, MA, United States
 
Comparing Deep Learning Extracted Features with Human-Designed Hydrological Indices and Evaluating Their Utilization in Flow Regime Classification (528471)
Weigang Tang, McMaster University, Hamilton, ON, Canada and Sean Carey, McMaster University, School of Geography and Earth Sciences, Hamilton, ON, Canada
 
Combining Unsupervised and Supervised Machine Learning for Quantifying Watershed Organization and Functions Based on High-resolution Airborne Remote Sensing Data (549357)
Haruko M Wainwright1, Nicola Falco2, Jashvina Devadoss3, Baptiste Dafflon2, Sebastian Uhlemann4, Michelle E Newcomer3, Maya Franklin5, Charuleka Varadharajan6, Roelof Versteeg7, Eoin Brodie2, Nicholas Bouskill6, James Bentley Brown8, Karl Bernard Schaettle9, Burke J Minsley10, Jeffery Deems11, Brian Joseph Enquist12, Kenneth Hurst Williams13 and Susan Hubbard2, (1)Lawrence Berkeley National Laboratory, Climate and Ecosystem Sciences Division, Berkeley, CA, United States, (2)Lawrence Berkeley National Laboratory, Earth and Environmental Sciences, Berkeley, CA, United States, (3)University of California Berkeley, Berkeley, CA, United States, (4)British Geological Survey Keyworth, Nottinghamshire, United Kingdom, (5)Lawrence Berkeley National Laboratory, Berkeley, United States, (6)Lawrence Berkeley National Lab, Berkeley, CA, United States, (7)Subsurface Insights, Hanover, NH, United States, (8)Lawrence Berkeley National Laboratory, Environmental Genomics and Systems Biology, Berkeley, CA, United States, (9)University of California Berkeley, Departments of Chemistry, Bioengineering, Chemical and Biomolecular Engineering, Berkeley, CA, United States, (10)USGS Geology, Geophysics, and Geochemistry Science Center, Denver, CO, United States, (11)National Snow and Ice Data Center, Boulder, United States, (12)University of Arizona, Ecology and Evolutionary Biology, Tucson, AZ, United States, (13)Colorado School of Mines, Golden, CO, United States
 
Improving Urban Flood Modeling with the Integration of Novel Data Sources (569937)
Ashish Shrestha1, Margaret Ellen Garcia1 and Giuseppe Mascaro2, (1)Arizona State University, School of Sustainable Engineering and the Built Environment, Tempe, AZ, United States, (2)Arizona State University, Tempe, AZ, United States
 
Spatial fuzzy committee of hydrological models applied to the Jiboa river basin in Salvador (583016)
Gerald Corzo, IHE Delft Institute for Water Education, Hydroinformatics, Delft, Netherlands, Mostafa Farrag, GFZ German Research Centre for Geosciences, Potsdam, brandenburg, Germany and Dimitri P Solomatine, IHE Delft Institute for Water Education, Delft, Netherlands
 
Deducing Dominant Drivers of Discharge Dynamics: A Mechanistic Modeling Framework to Simultaneously Test Multiple Hypotheses (586659)
Nathan Reaver, University of Florida, Water Institute, Gainesville, FL, United States, David A Kaplan, University of Florida, Environmental Engineering Sciences, Gainesville, FL, United States, Harald Klammer, University of Florida - UF, Engineering School of Sustainable Infrastructure & Environment, Gainesville, FL, United States and James W Jawitz, University of Florida, Soil and Water Sciences, Gainesville, FL, United States
 
Explaining the shifts in hydrological response due to multiyear drought and subsequent recovery or non-recovery (590722)
Margarita Saft, Murray Cameron Peel and Tim J Peterson, The University of Melbourne, Parkville, VIC, Australia
 
Combination of Gaussian process and spatial statistics for interpolation applications, a comparison with Artificial Neural Networks (593125)
Emmanouil Varouchakis, Zoetermeer, South Holland, Netherlands, Gerald Corzo, UNESCO-IHE� Institute for Water Education, HYDROINFORMATICS, Delft, Netherlands and Mostafa Farrag, GFZ German Research Centre for Geosciences, Potsdam, brandenburg, Germany
 
Generating high-resolution precipitation data using advanced machine learning at the basin scale (607227)
Utkarsh Mital1, Dipankar Dwivedi1, James Bentley Brown2, Carl I Steefel3 and Scott L Painter4, (1)Lawrence Berkeley National Laboratory, Berkeley, CA, United States, (2)Lawrence Berkeley National Laboratory, Environmental Genomics and Systems Biology, Berkeley, CA, United States, (3)Lawrence Berkeley National Laboratory, Earth and Environmental Sciences, Berkeley, CA, United States, (4)Oak Ridge National Laboratory, Oak Ridge, TN, United States
 
Exploiting Artificial Intelligence for Advancing Earth and Environmental System Science (Invited) (629941)
Forrest M. Hoffman1, Jitendra Kumar2, Zachary Lance Langford3, Venkata Shashank Konduri4 and Nathan Collier1, (1)Oak Ridge National Laboratory, Computational Earth Sciences, Oak Ridge, TN, United States, (2)Oak Ridge National Laboratory, Climate Change Science Institute and Environmental Sciences Division, Oak Ridge, TN, United States, (3)Oak Ridge National Laboratory, Oak Ridge, TN, United States, (4)Northeastern University, Civil and Environmental Engineering, Boston, MA, United States
See more of: Hydrology
<< Previous Session Proposal | Next Session Proposal >>