A multiscale deep learning model for soil moisture integrating satellite and in-situ data

Liu, Jiangtao; Rahmani, Farshid; Lawson, Kathryn; Shen, Chaopeng

doi:10.5281/zenodo.6314345

Title: A multiscale deep learning model for soil moisture integrating satellite and in-situ data

Dataset
Other Related Research

Abstract

Model codes for the article: "A multiscale deep learning model for soil moisture integrating satellite and in-situ data"

Authors:

Liu, Jiangtao; Rahmani, Farshid; Lawson, Kathryn; Shen, Chaopeng

Pennsylvania State Univ., University Park, PA (United States); Pennsylvania State Univ., University Park, PA (United States)
Pennsylvania State Univ., University Park, PA (United States)

Publication Date:: Mon Feb 28 04:00:00 UTC 2022

DOE Contract Number:: SC0016605

Research Org.:: Univ. of California, Davis, CA (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Biological and Environmental Research (BER)

Subject:: 54 ENVIRONMENTAL SCIENCES; LSTM; deep learning; in situ; multiscale; resolution effect; soil moisture

OSTI Identifier:: 2217666

DOI:: https://doi.org/10.5281/zenodo.6314345

Citation Formats


                    Liu, Jiangtao, Rahmani, Farshid, Lawson, Kathryn, and Shen, Chaopeng. A multiscale deep learning model for soil moisture integrating satellite and in-situ data.  United States: N. p., 2022. 
        Web.  doi:10.5281/zenodo.6314345.

Copy to clipboard


                    Liu, Jiangtao, Rahmani, Farshid, Lawson, Kathryn, & Shen, Chaopeng. A multiscale deep learning model for soil moisture integrating satellite and in-situ data.  United States.  doi:https://doi.org/10.5281/zenodo.6314345

Copy to clipboard


                    Liu, Jiangtao, Rahmani, Farshid, Lawson, Kathryn, and Shen, Chaopeng. 2022.  
"A multiscale deep learning model for soil moisture integrating satellite and in-situ data".  United States.  doi:https://doi.org/10.5281/zenodo.6314345.  https://www.osti.gov/servlets/purl/2217666. Pub date:Mon Feb 28 04:00:00 UTC 2022

Copy to clipboard


                    
@article{osti_2217666,

  title        = {A multiscale deep learning model for soil moisture integrating satellite and in-situ data},

  author       = {Liu, Jiangtao and Rahmani, Farshid and Lawson, Kathryn and Shen, Chaopeng},

  abstractNote = {Model codes for the article: "A multiscale deep learning model for soil moisture integrating satellite and in-situ data"},

  doi          = {10.5281/zenodo.6314345},

  journal      = {},

  number       = ,

  volume       = ,

  place        = {United States},

  year         = {Mon Feb 28 04:00:00 UTC 2022},

  month        = {Mon Feb 28 04:00:00 UTC 2022}

}

Copy to clipboard

Dataset:

View Dataset

DOI: https://doi.org/10.5281/zenodo.6314345

Save / Share:

Export Metadata

Save to My Library

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

A Multiscale Deep Learning Model for Soil Moisture Integrating Satellite and In Situ Data

Journal Article Liu, Jiangtao ; Rahmani, Farshid ; Lawson, Kathryn ; ... - Geophysical Research Letters

Deep learning (DL) models trained on hydrologic observations can perform extraordinarily well, but they can inherit deficiencies of the training data, such as limited coverage of in situ data or low resolution/accuracy of satellite data. In this work, we propose a novel multiscale DL scheme learning simultaneously from satellite and in situ data to predict 9 km daily soil moisture (5 cm depth). Based on spatial cross-validation over sites in the conterminous United States, the multiscale scheme obtained a median correlation of 0.901 and root-mean-square error of 0.034 m³/m³. It outperformed the Soil Moisture Active Passive satellite mission's 9 kmmore »« less
A Multiscale Deep Learning Model for Soil Moisture Integrating Satellite and In Situ Data

Journal Article Liu, Jiangtao ; Rahmani, Farshid ; Lawson, Kathryn ; ... - Geophysical Research Letters

Abstract Deep learning (DL) models trained on hydrologic observations can perform extraordinarily well, but they can inherit deficiencies of the training data, such as limited coverage of in situ data or low resolution/accuracy of satellite data. Here we propose a novel multiscale DL scheme learning simultaneously from satellite and in situ data to predict 9 km daily soil moisture (5 cm depth). Based on spatial cross‐validation over sites in the conterminous United States, the multiscale scheme obtained a median correlation of 0.901 and root‐mean‐square error of 0.034 m ³ /m ³ . It outperformed the Soil Moisture Active Passive satellite mission's 9 km product,more »« less
Multiscale ACI Satellite Database

Dataset Christensen, Matthew ; Geiss, Anrew V ; Varble, Adam C ; ...

The SATELLITE_EAGLES_PNNL NetCDF dataset contains a suite of satellite- and reanalysis-derived atmospheric and surface parameters on a regular latitude–longitude grid. The dataset includes core geophysical fields such as land fraction, aerosol optical depth at multiple wavelengths (465, 550, 667, and 865 nm), sea surface temperature, estimated inversion strength, and various thermodynamic and dynamic quantities (e.g., relative humidity, vertical velocity, boundary-layer height, and surface fluxes) from both MERRA and ERA reanalysis products, provided as daily-mean and instantaneous values. A major component of the dataset consists of MODIS-retrieved cloud microphysical properties, including cloud droplet number concentration, cloud effective radius, optical thickness, andmore »« less
Multiscale ACI Satellite Database

Dataset Christensen, Matthew ; Geiss, Andrew V ; Varble, Adam C ; ...

The SATELLITE_EAGLES_PNNL NetCDF dataset contains a suite of satellite- and reanalysis-derived atmospheric and surface parameters on a regular latitude–longitude grid. The dataset includes core geophysical fields such as land fraction, aerosol optical depth at multiple wavelengths (465, 550, 667, and 865 nm), sea surface temperature, estimated inversion strength, and various thermodynamic and dynamic quantities (e.g., relative humidity, vertical velocity, boundary-layer height, and surface fluxes) from both MERRA and ERA reanalysis products, provided as daily-mean and instantaneous values. A major component of the dataset consists of MODIS-retrieved cloud microphysical properties, including cloud droplet number concentration, cloud effective radius, optical thickness, andmore »« less
ORNL FACE Soil Moisture Data

Dataset Tharp, M.L. ; Norby, R.J.

On the FACE site, soil moisture data are available for ring 1 through ring 5 from 1997-2007, and there are data for ring 6from 1997-1999. Ring 1 and ring 2 are exposed to elevated CO2, and the remaining rings have ambient CO2. Soil moisture was measured with a time-domain reflectometer(TRASE systems, Soil Moisture Equipment Corporation,Santa Barbara, CA) to a depth of 20cm. The missing-value indicator for the soil moisture data is -99.99.

Similar Records