What is it about?

Soil moisture estimation is a prominent task in hydrology that people have been working on for a long time. With the advances in deep learning and remote sensing, we see promise in the application of these methods to the task of soil moisture estimation for improved performance. We obtain better results than most existing methods and our methods generalize well to unseen regions.

Featured Image

Why is it important?

Soil moisture is a key variable in various agriculture and water management systems. Accurate and high-resolution estimates of soil moisture have multiple downstream benefits such as reduced water wastage by better understanding and managing the consumption of water, utilizing smarter irrigation methods and effective canal water management. Soil moisture is also a key variable in drought estimation and erosion. We develop a deep learning–based model that estimates the volumetric soil moisture content in the top ∼5 cm of soil at a nominal 320-m resolution. Our results demonstrate that deep learning is a useful tool for fusing different modalities with ease, while producing high-resolution models that are not location specific.


Accurate, global high resolution estimates of soil moisture transform the landscape for the multitude of downstream tasks that utilize soil moisture readings and I am glad to see the application of advances in deep learning be applied to traditional hydrology tasks.

Vishal Batchu

Read the Original

This page is a summary of: A Deep Learning Data Fusion Model using Sentinel-1/2, SoilGrids, SMAP-USDA, and GLDAS for Soil Moisture Retrieval, Journal of Hydrometeorology, February 2023, American Meteorological Society,
DOI: 10.1175/jhm-d-22-0118.1.
You can read the full text:



The following have contributed to this page