Skip to main content
U.S. flag

An official website of the United States government

Publication Date
30 March 2022

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

Subtitle
Learning simultaneously from satellite and in situ data improved predictions and avoided limitations of individual datasets.
Print / PDF
Powerpoint Slide
Science

A novel multiscale deep learning scheme learned simultaneously from satellite and in situ data to predict 9 km daily soil moisture; such a multi-input model has not previously been achieved. 

Impact

The multiscale product is useful for planning against floods, droughts, and pests, and the scheme is generically applicable to geoscientific domains with data on multiple scales, breaking the confines of individual data sets. 

Summary

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 m3/m3. It outperformed the Soil Moisture Active Passive satellite mission's 9 km product, DL models trained on in situ data alone, and land surface models. Our 9 km product showed better accuracy than previous 1 km satellite downscaling products, highlighting the limited impacts of improving resolution. Not only is our product useful for planning against floods, droughts, and pests, our scheme is generically applicable to geoscientific domains with data on multiple scales, breaking the confines of individual data sets. 

Point of Contact
Chaopeng Shen
Institution(s)
Pennsylvania State University
Funding Program Area(s)
Publication