Litcius/Paper detail

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

Jiangtao Liu, Farshid Rahmani, Kathryn Lawson, Chaopeng Shen

2022Geophysical Research Letters101 citationsDOIOpen Access PDF

Abstract

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, 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 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.

Topics & Concepts

DownscalingSatelliteEnvironmental scienceRemote sensingIn situEarth observationWater contentMean squared errorSatellite imageryMeteorologyDeep learningData assimilationComputer scienceMachine learningGeologyGeographyMathematicsStatisticsPrecipitationGeotechnical engineeringAerospace engineeringEngineeringSoil Moisture and Remote SensingPrecipitation Measurement and AnalysisLandslides and related hazards
A Multiscale Deep Learning Model for Soil Moisture Integrating Satellite and In Situ Data | Litcius