Estimating Watershed Subsurface Permeability From Stream Discharge Data using Deep Neural Networks, Frontiers in Earth Science: Dataset

Cromwell, Erol; Shuai, Pin; Jiang, Peishi; Coon, Ethan; Painter, Scott; Moulton, David; Lin, Youzuo; Chen, Xingyuan

doi:10.15485/1756193

Title: Estimating Watershed Subsurface Permeability From Stream Discharge Data using Deep Neural Networks, Frontiers in Earth Science: Dataset

Dataset
Other Related Research

Abstract

This data package contains watershed modeling inputs and outputs as well as deep neural networks training and testing results used in "Estimating Watershed Subsurface Permeability From Stream Discharge Data using Deep Neural Networks" (Cromwell et al., 2021). We train various deep neural network models with different architectures to predict subsurface permeability from stream discharge hydrograph at the watershed outlet. The training data are obtained from ensemble simulations of hydrographs corresponding to an permeability ensemble using a fully-distributed, integrated surface-subsurface hydrologic model. The trained model is then applied to estimate the permeability of the real watershed using its observed hydrograph at the outlet. Our study demonstrates that the permeabilities of the soil and geologic facies that make significant contributions to the outlet discharge can be more accurately estimated from the discharge data. Their estimations are also more robust with observation errors. Compared to the traditional ensemble smoother method, DNNs show stronger performance in capturing the nonlinear relationship between permeability and stream hydrograph to accurately estimate permeability. Our study sheds new light on the value of the emerging deep learning methods in assisting integrated watershed modeling by improving parameter estimation, which will eventually reduce the uncertainty in predictive watershed models. For detailedmore »« less

Authors:

Cromwell, Erol;

; Jiang, Peishi; Coon, Ethan; Painter, Scott; Moulton, David; Lin, Youzuo;

Pacific Northwest National Laboratory; Pacific Northwest National Laboratory
Pacific Northwest National Laboratory
Oak Ridge National Laboratory
Los Alamos National Laboratory

Publication Date:: Wed Jan 01 04:00:00 UTC 2020

Research Org.:: Environmental System Science Data Infrastructure for a Virtual Ecosystem; ExaSheds

Sponsoring Org.:: U.S. DOE > Office of Science > Biological and Environmental Research (BER)

Subject:: 54 ENVIRONMENTAL SCIENCES; Deep Neural Networks; EARTH SCIENCE > TERRESTRIAL HYDROSPHERE > GROUND WATER; EARTH SCIENCE > TERRESTRIAL HYDROSPHERE > SURFACE WATER; EARTH SCIENCE > TERRESTRIAL HYDROSPHERE > SURFACE WATER > SURFACE WATER PROCESSES/MEASUREMENTS > DISCHARGE/FLOW > AVERAGE FLOW; Watershed modeling

OSTI Identifier:: 1756193

DOI:: https://doi.org/10.15485/1756193

Citation Formats


                    Cromwell, Erol, Shuai, Pin, Jiang, Peishi, Coon, Ethan, Painter, Scott, Moulton, David, Lin, Youzuo, and Chen, Xingyuan. Estimating Watershed Subsurface Permeability From Stream Discharge Data using Deep Neural Networks, Frontiers in Earth Science: Dataset.  United States: N. p., 2020. 
        Web.  doi:10.15485/1756193.

Copy to clipboard


                    Cromwell, Erol, Shuai, Pin, Jiang, Peishi, Coon, Ethan, Painter, Scott, Moulton, David, Lin, Youzuo, & Chen, Xingyuan. Estimating Watershed Subsurface Permeability From Stream Discharge Data using Deep Neural Networks, Frontiers in Earth Science: Dataset.  United States.  doi:https://doi.org/10.15485/1756193

Copy to clipboard


                    Cromwell, Erol, Shuai, Pin, Jiang, Peishi, Coon, Ethan, Painter, Scott, Moulton, David, Lin, Youzuo, and Chen, Xingyuan. 2020.  
"Estimating Watershed Subsurface Permeability From Stream Discharge Data using Deep Neural Networks, Frontiers in Earth Science: Dataset".  United States.  doi:https://doi.org/10.15485/1756193.  https://www.osti.gov/servlets/purl/1756193. Pub date:Wed Jan 01 04:00:00 UTC 2020

Copy to clipboard


                    
@article{osti_1756193,

  title        = {Estimating Watershed Subsurface Permeability From Stream Discharge Data using Deep Neural Networks, Frontiers in Earth Science: Dataset},

  author       = {Cromwell, Erol and Shuai, Pin and Jiang, Peishi and Coon, Ethan and Painter, Scott and Moulton, David and Lin, Youzuo and Chen, Xingyuan},

  abstractNote = {This data package contains watershed modeling inputs and outputs as well as deep neural networks training and testing results used in "Estimating Watershed Subsurface Permeability From Stream Discharge Data using Deep Neural Networks" (Cromwell et al., 2021). We train various deep neural network models with different architectures to predict subsurface permeability from stream discharge hydrograph at the watershed outlet. The training data are obtained from ensemble simulations of hydrographs corresponding to an permeability ensemble using a fully-distributed, integrated surface-subsurface hydrologic model. The trained model is then applied to estimate the permeability of the real watershed using its observed hydrograph at the outlet. Our study demonstrates that the permeabilities of the soil and geologic facies that make significant contributions to the outlet discharge can be more accurately estimated from the discharge data. Their estimations are also more robust with observation errors. Compared to the traditional ensemble smoother method, DNNs show stronger performance in capturing the nonlinear relationship between permeability and stream hydrograph to accurately estimate permeability. Our study sheds new light on the value of the emerging deep learning methods in assisting integrated watershed modeling by improving parameter estimation, which will eventually reduce the uncertainty in predictive watershed models. For detailed information regarding watershed model description and DNNs setup, please refer to Cromwell et al., 2021. The deep_learning.zip file contains the inputs and outputs for the different deep neural networks. The watershed_model.zip file contains the inputs and outputs for watershed simulation using ATS. The figures.zip file contains raw figures and their corresponding scripts. For a more detailed description, please see the README.md file within each compressed file.},

  doi          = {10.15485/1756193},

  journal      = {},

  number       = ,

  volume       = ,

  place        = {United States},

  year         = {Wed Jan 01 04:00:00 UTC 2020},

  month        = {Wed Jan 01 04:00:00 UTC 2020}

}

Copy to clipboard

Dataset:

View Dataset

DOI: https://doi.org/10.15485/1756193

Save / Share:

Export Metadata

Save to My Library

Similar records in DOE Data Explorer and OSTI.GOV collections:

Estimating Watershed Subsurface Permeability From Stream Discharge Data Using Deep Neural Networks

Journal Article Cromwell, Erol L. D. ; Shuai, Pin ; Jiang, Peishi ; ... - Frontiers in Earth Science

Subsurface permeability is a key parameter in watershed models that controls the contribution from the subsurface flow to stream flows. Since the permeability is difficult and expensive to measure directly at the spatial extent and resolution required by fully distributed watershed models, estimation through inverse modeling has had a long history in subsurface hydrology. The wide availability of stream surface flow data, compared to groundwater monitoring data, provides a new data source to infer soil and geologic properties using integrated surface and subsurface hydrologic models. As most of the existing methods have shown difficulty in dealing with highly nonlinear inversemore »« less
Estimating Watershed Subsurface Permeability From Stream Discharge Data Using Deep Neural Networks

Journal Article Cromwell, Erol ; Shuai, Pin ; Jiang, Peishi ; ... - Frontiers in Earth Science

Subsurface permeability is a key parameter in watershed models that controls the contribution from the subsurface flow to stream flows. Since the permeability is difficult and expensive to measure directly at the spatial extent and resolution required by fully distributed watershed models, estimation through inverse modeling has had a long history in subsurface hydrology. The wide availability of stream surface flow data, compared to groundwater monitoring data, provides a new data source to infer soil and geologic properties using integrated surface and subsurface hydrologic models. As most of the existing methods have shown difficulty in dealing with highly nonlinear inversemore »« less
Dataset and scripts for manuscript "Using Neural Network Ensembles to Separate Ocean Biogeochemical and Physical Drivers of Phytoplankton Biogeography in Earth System Models"

Dataset Holder, Christopher ; Gnanadesikan, Anand ; Aude-Pradal, Marie

Please note: The title of this version contains an updated title for the manuscript compared to the previous version of this dataset. This is only due to title updates during the peer review process for the manuscript. The zip file contains the scripts, functions, and source files for the manuscript titled "Using Neural Network Ensembles to Separate Ocean Biogeochemical and Physical Drivers of Phytoplankton Biogeography in Earth System Models." The manuscript has been submitted for peer review. Please consult the README file for information on the specifications of the files. These files may occasionally be updated to add annotations tomore »« less
Stream discharge and temperature data collected within the East and Taylor Watershed, Colorado for the Lawrence Berkeley National Laboratory Watershed Function Science Focus Area (water years 2019 to 2024)

Dataset Carroll, Rosemary ; Beutler, Curtis ; Shirley, Austin ; ...

This data package contains East and Taylor Watershed, Colorado stream discharge and temperature data for water years 2019 to 2024. This data was collected to understand hydrological processes occurring in the East River and Taylor River Watersheds, Colorado, which is part of the Lawrence Berkeley National Laboratory Watershed Function Scientific Focus Area. Data includes instantaneous observed discharge using salt dillution and acoustic doppler velocimeter techniques, raw pressure transducer downloaded data, sub-hourly temperature as well as corrected water level and associated stream discharge and mean daily values. Notes on water level corrections, rating curve development and metadata provided. A rating curvemore »« less
Walker Branch Watershed: 15-minute and Daily Stream Discharge and Annual Runoff

Dataset Mulholland, P.J. ; Griffiths, N.A.

This data set reports 15-minute and daily stream discharge, and annual runoff for the West and East Forks draining Walker Branch Watershed (WBW). The long-term Walker Branch Hydrology Monitoring project was intended to document changes in the water balance (precipitation inputs, stream discharge outputs) for the WBW over time. This data set contains three data files of stream discharge (L/s) for 15-minute and daily intervals, and annual runoff (cm). The daily and annual datasets began in 1969 in both East and West Forks, while the 15-minute datasets began in 1994 in both Forks. Data were collected through 2014 for themore »« less

Similar Records