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

Jiangtao Liu, Farshid Rahmani, Kathryn Lawson, Chaopeng Shen

Research output: Contribution to journalArticlepeer-review

14 Scopus citations


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 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.

Original languageEnglish (US)
Article numbere2021GL096847
JournalGeophysical Research Letters
Issue number7
StatePublished - Apr 16 2022

All Science Journal Classification (ASJC) codes

  • Geophysics
  • Earth and Planetary Sciences(all)


Dive into the research topics of 'A Multiscale Deep Learning Model for Soil Moisture Integrating Satellite and In Situ Data'. Together they form a unique fingerprint.

Cite this