skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Prolongation of SMAP to Spatiotemporally Seamless Coverage of Continental U.S. Using a Deep Learning Neural Network

Abstract

The Soil Moisture Active Passive (SMAP) mission has delivered valuable sensing of surface soil moisture since 2015. However, it has a short time span and irregular revisit schedules. Utilizing a state-of-the-art time series deep learning neural network, Long Short-Term Memory (LSTM), we created a system that predicts SMAP level-3 moisture product with atmospheric forcings, model-simulated moisture, and static physiographic attributes as inputs. The system removes most of the bias with model simulations and improves predicted moisture climatology, achieving small test root-mean-square errors (<0.035) and high-correlation coefficients >0.87 for over 75% of Continental United States, including the forested southeast. As the first application of LSTM in hydrology, we show the proposed network avoids overfitting and is robust for both temporal and spatial extrapolation tests. LSTM generalizes well across regions with distinct climates and environmental settings. With high fidelity to SMAP, LSTM shows great potential for hindcasting, data assimilation, and weather forecasting.

Authors:
ORCiD logo [1]; ORCiD logo [1];  [1];  [1]
  1. Pennsylvania State Univ., University Park, PA (United States)
Publication Date:
Research Org.:
Pennsylvania State Univ., University Park, PA (United States)
Sponsoring Org.:
USDOE Office of Science (SC)
OSTI Identifier:
1537301
Grant/Contract Number:  
SC0010620
Resource Type:
Accepted Manuscript
Journal Name:
Geophysical Research Letters
Additional Journal Information:
Journal Volume: 44; Journal Issue: 21; Journal ID: ISSN 0094-8276
Publisher:
American Geophysical Union
Country of Publication:
United States
Language:
English
Subject:
54 ENVIRONMENTAL SCIENCES; Geology

Citation Formats

Fang, Kuai, Shen, Chaopeng, Kifer, Daniel, and Yang, Xiao. Prolongation of SMAP to Spatiotemporally Seamless Coverage of Continental U.S. Using a Deep Learning Neural Network. United States: N. p., 2017. Web. doi:10.1002/2017gl075619.
Fang, Kuai, Shen, Chaopeng, Kifer, Daniel, & Yang, Xiao. Prolongation of SMAP to Spatiotemporally Seamless Coverage of Continental U.S. Using a Deep Learning Neural Network. United States. doi:10.1002/2017gl075619.
Fang, Kuai, Shen, Chaopeng, Kifer, Daniel, and Yang, Xiao. Mon . "Prolongation of SMAP to Spatiotemporally Seamless Coverage of Continental U.S. Using a Deep Learning Neural Network". United States. doi:10.1002/2017gl075619. https://www.osti.gov/servlets/purl/1537301.
@article{osti_1537301,
title = {Prolongation of SMAP to Spatiotemporally Seamless Coverage of Continental U.S. Using a Deep Learning Neural Network},
author = {Fang, Kuai and Shen, Chaopeng and Kifer, Daniel and Yang, Xiao},
abstractNote = {The Soil Moisture Active Passive (SMAP) mission has delivered valuable sensing of surface soil moisture since 2015. However, it has a short time span and irregular revisit schedules. Utilizing a state-of-the-art time series deep learning neural network, Long Short-Term Memory (LSTM), we created a system that predicts SMAP level-3 moisture product with atmospheric forcings, model-simulated moisture, and static physiographic attributes as inputs. The system removes most of the bias with model simulations and improves predicted moisture climatology, achieving small test root-mean-square errors (<0.035) and high-correlation coefficients >0.87 for over 75% of Continental United States, including the forested southeast. As the first application of LSTM in hydrology, we show the proposed network avoids overfitting and is robust for both temporal and spatial extrapolation tests. LSTM generalizes well across regions with distinct climates and environmental settings. With high fidelity to SMAP, LSTM shows great potential for hindcasting, data assimilation, and weather forecasting.},
doi = {10.1002/2017gl075619},
journal = {Geophysical Research Letters},
number = 21,
volume = 44,
place = {United States},
year = {2017},
month = {10}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 20 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Implementation of Noah land surface model advances in the National Centers for Environmental Prediction operational mesoscale Eta model
journal, November 2003

  • Ek, M. B.; Mitchell, K. E.; Lin, Y.
  • Journal of Geophysical Research: Atmospheres, Vol. 108, Issue D22
  • DOI: 10.1029/2002JD003296

The Soil Moisture Active Passive (SMAP) Mission
journal, May 2010


Evaluation of soil moisture in CMIP5 simulations over the contiguous United States using in situ and satellite observations
journal, January 2017


Regional Soil Moisture Biases and Their Influence on WRF Model Temperature Forecasts over the Intermountain West
journal, February 2016

  • Massey, Jeffrey D.; Steenburgh, W. James; Knievel, Jason C.
  • Weather and Forecasting, Vol. 31, Issue 1
  • DOI: 10.1175/WAF-D-15-0073.1

Global Retrospective Estimation of Soil Moisture Using the Variable Infiltration Capacity Land Surface Model, 1980–93
journal, April 2001


Daily reservoir inflow forecasting using multiscale deep feature learning with hybrid models
journal, January 2016


The AI detectives
journal, July 2017


Deep learning
journal, May 2015

  • LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
  • Nature, Vol. 521, Issue 7553
  • DOI: 10.1038/nature14539

A Data-Driven Approach for Daily Real-Time Estimates and Forecasts of Near-Surface Soil Moisture
journal, March 2017

  • Koster, Randal D.; Reichle, Rolf H.; Mahanama, Sarith P. P.
  • Journal of Hydrometeorology, Vol. 18, Issue 3
  • DOI: 10.1175/JHM-D-16-0285.1

Improving the representation of hydrologic processes in Earth System Models: REPRESENTING HYDROLOGIC PROCESSES IN EARTH SYSTEM MODELS
journal, August 2015

  • Clark, Martyn P.; Fan, Ying; Lawrence, David M.
  • Water Resources Research, Vol. 51, Issue 8
  • DOI: 10.1002/2015WR017096

Comparison of NLDAS-2 Simulated and NASMD Observed Daily Soil Moisture. Part I: Comparison and Analysis
journal, October 2015

  • Xia, Youlong; Ek, Michael B.; Wu, Yihua
  • Journal of Hydrometeorology, Vol. 16, Issue 5
  • DOI: 10.1175/JHM-D-14-0096.1

A catchment-based approach to modeling land surface processes in a general circulation model: 1. Model structure
journal, October 2000

  • Koster, Randal D.; Suarez, Max J.; Ducharne, Agnès
  • Journal of Geophysical Research: Atmospheres, Vol. 105, Issue D20
  • DOI: 10.1029/2000JD900327

Validation of SMAP surface soil moisture products with core validation sites
journal, March 2017


Long Short-Term Memory
journal, November 1997


Flash flood warning based on rainfall thresholds and soil moisture conditions: An assessment for gauged and ungauged basins
journal, December 2008


Regions of Strong Coupling Between Soil Moisture and Precipitation
journal, August 2004


The components of a ‘SVAT’ scheme and their effects on a GCM's hydrological cycle
journal, January 1994


Development and evaluation of Soil Moisture Deficit Index (SMDI) and Evapotranspiration Deficit Index (ETDI) for agricultural drought monitoring
journal, November 2005


Analysis of soil moisture memory from observations in Europe: SOIL MOISTURE MEMORY IN OBSERVATIONS
journal, August 2012

  • Orth, R.; Seneviratne, S. I.
  • Journal of Geophysical Research: Atmospheres, Vol. 117, Issue D15
  • DOI: 10.1029/2011JD017366

Improving Budyko curve-based estimates of long-term water partitioning using hydrologic signatures from GRACE: PREDICTING DEPARTURE FROM BUDYKO USING GRACE
journal, July 2016

  • Fang, Kuai; Shen, Chaopeng; Fisher, Joshua B.
  • Water Resources Research, Vol. 52, Issue 7
  • DOI: 10.1002/2016WR018748

An Evaluation of the North American Regional Reanalysis Simulated Soil Moisture Conditions during the 2011–13 Drought Period
journal, February 2017

  • Leeper, Ronald D.; Bell, Jesse E.; Vines, Chanté
  • Journal of Hydrometeorology, Vol. 18, Issue 2
  • DOI: 10.1175/JHM-D-16-0132.1

Confronting Weather and Climate Models with Observational Data from Soil Moisture Networks over the United States
journal, April 2016

  • Dirmeyer, Paul A.; Wu, Jiexia; Norton, Holly E.
  • Journal of Hydrometeorology, Vol. 17, Issue 4
  • DOI: 10.1175/JHM-D-15-0196.1