Predicting near-surface soil moisture from remote sensing indices using machine learning methods

Remote Sensing for Environmental Monitoring

Authors

First and Last Name Academic degree E-mail Affiliation
Oleksii Piskunov No piskunovalxy [at] gmail.com Dnipro University of Technology
Dnipro, Ukraine
Oleh Tiapkin Sc.D. tiapkin.oleh [at] gmail.com Dnipro University of Technology
Dnipro, Ukraine
Andrii Lozovyi Ph.D. lozovoy_dp_ua [at] ukr.net Dnipro University of Technology
Dnipro, Ukraine
Olha Medvedieva Sc.D. medvedevaolga1702 [at] gmail.com M.S. Poliakov Institute of Geotechnical Mechanics of NAS of Ukraine
Dnipro, Ukraine

I and my co-authors (if any) authorize the use of the Paper in accordance with the Creative Commons CC BY license

First published on this website: 11.08.2025 - 13:07
Abstract 

The regional assessment of near-surface soil moisture is essential for agricultural and environmental monitoring. Although it frequently facing difficulties due to insufficient in-situ measurements. This study investigates a machine learning approach to predict soil moisture fracture utilizing publicly accessible remote sensing data, such as vegetation indices, land surface temperature and topography details. An example dataset from an agricultural region in northwestern Spain (Zamora region) including satellite observations with in-situ measurements, functioned as a testbed for creating an Extreme Gradient Boosting model.

The model showed a promising ability to predict soil moisture using transferable data. The initial findings suggest that the methodology can provide insights for regional soil moisture evaluation, helping applications such as drought monitoring and water resource management, especially in places where direct measurements are not available. Further validation in different settings is required to determine wider applicability.

References 

Dorigo, W. A., Xaver, A., Vreugdenhil, M., Gruber, A., Hegyiová, A., Sanchis-Dufau, A. D., Zamojski, D., Cordes, C., Wagner, W., & Van Der Schalie, R. (2021). The International Soil Moisture Network: serving Earth system science for over a decade. Hydrology and Earth System Sciences, 25(11), 5749-5804. https://doi.org/10.5194/hess-25-5749-2021

Imtiaz, F., Farooque, A. A., Randhawa, G. S., Wang, X., Esau, T. J., Acharya, B., & Hashemi Garmdareh, S. E. (2024). An inclusive approach to crop soil moisture estimation: Leveraging satellite thermal infrared bands and vegetation indices on Google Earth engine. Agricultural Water Management, 306, 109172. https://doi.org/10.1016/j.agwat.2024.109172

Lamichhane, M., Mehan, S., & Mankin, K. R. (2025). Soil Moisture Prediction Using Remote Sensing and Machine Learning Algorithms: A Review on Progress, Challenges, and Opportunities. Remote Sensing17(14), 2397. https://doi.org/10.3390/rs17142397

Pigulevskiy, P., Svistun, V., Slobodyaniuk, S., Kyryliuk, A. (2016). Studying of modern flooding of southwestern part Krivbass by geophysical methods. Geoinformatics 2016 - XVth International Conference on Geoinformatics - Theoretical and Applied Aspects, https://doi.org/10.3997/2214-4609.201600477

Tiapkin, O..K., Onyshchenko, S. A., Piskunov, O. V. (2025). Engineering-ecological research of the upper part of geological section using seismic data. Geofizychnyi Zhurnal, 47(2), 150-155. https://doi.org/10.24028/gj.v47i2.322491

Yamazaki, D., Trigg, M. A., Ikeshima, D., et al. (2022). MERIT Hydro: A High-Resolution Global Hydrography Map Derived From Latest Elevation Data. Water Resources Research, 58(10), https://doi.org/10.1029/2019WR024873