This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Journal Menu
By: Hem Chandra Joshi and Aadarsh Joshi.
IIMT University, Meerut; H.O.D Computer Science Department, Mind-Power-University, Bhimtal
Abstract: Soil moisture is a critical Earth system variable linking atmospheric, hydrological, and ecological processes. However, observations are sparse and fragmented: in situ gauges provide point data, satellite missions (SMAP, SMOS, Sentinel-1) offer broad coverage at coarse resolutionQ, and land‐surface models (GLDAS, ERA5, etc.) yield estimates with their own biase. Here we propose a conceptual framework for integrated environmental data modelling, combining rainfall, temperature, and soil moisture information with machine learning (ML) to enhance predictive capability. The framework envisions fusing multi-source data (meteorological reanalysis, remote sensing products, ground networks, vegetation indices) into a unified feature set, then applying interpretable ML models to forecast soil moisture and related hydrological states. We review recent advances: ML‐based global soil moisture datasets (e.g., SoMo.ml), remote sensing retrievals and indices, and climate-driven modelling studies. We outline a data integration strategy with preprocessing steps and model training procedures. Preliminary insights suggest that ensemble ML models (Random Forest, XGBoost) effectively capture nonlinear climate–soil interactions, especially when multi-sensor inputs are used. The integrated approach can improve drought and water balance predictions by leveraging synergistic signals from rainfall, temperature, and vegetation. In sum, this conceptual study positions soil moisture prediction within a broader data-science environmental modelling paradigm, highlighting opportunities for data fusion and interdisciplinary analytics.
Citation:
Refrences:
- Arshad, S., Ashraf, A., Al-Dalahmeh, M., & Nazli, F. (2026). Enhancing assimilated soil moisture prediction from environmental data using advanced machine learning. Environmental Systems Research, 15, 5.
- Cao, F., Xie, Z., Wang, L., Ni, H., & Zhang, W. (2022). Stacking with CatBoost, Random Forest, and Gradient Boosting for soil moisture estimation using multispectral and thermal satellite indices. Remote Sensing, 14(13), 3185.
- Chango, N., Hamman, J. J., Duethmann, D., Uhe, P. F., Ban, H., & Zhang, H. (2023). Integrated framework for hydrologic modelling in data-sparse watersheds and climate change impact on projected green and blue water sustainability. Frontiers in Environmental Science, 11, 1233216. doi:10.3389/fenvs.2023.1233216
- Han, Q., Zeng, Y., Zhang, L., Wang, C., Prikaziuk, E., Niu, Z., & Su, B. (2023). Global long-term daily 1 km surface soil moisture dataset with physics-informed machine learning. Scientific Data, 10, 101. doi:10.1038/s41597-023-02011-7
- Lamichhane, M., Mehan, S., Mankin, K. R., Wang, G., Zeng, S., Ruan, Y., & Lu, X. (2025). Soil moisture prediction using remote sensing and machine learning algorithms: A review on progress, challenges, and opportunities. Remote Sensing, 17(14), 2397. doi:10.3390/rs17142397
- Li, S., Zhu, P., Song, N., Li, C., & Wang, J. (2023). Regional soil moisture estimation leveraging multi-source data fusion and automated machine learning. Remote Sensing, 17(5), 837. doi:10.3390/rs17050837
- Mimeau, L., Tramblay, Y., Brocca, L., Massari, C., Camici, S., & Finaud-Guyot, P. (2021). Modeling the response of soil moisture to climate variability in the Mediterranean region. Hydrology and Earth System Sciences, 25, 653–673. doi:10.5194/hess-25-653-2021
- O’Neill, S., & Orth, R. (2021). Global soil moisture data derived through machine learning trained with in-situ measurements. Scientific Data, 8, 170. doi:10.1038/s41597-021-00964-1
- Sivelle, V., Massari, C., Tramblay, Y., Filippucci, P., Dakhlaoui, H., Quintana-Seguí, P., Clavera-Gispert, R., Boutaghane, H., Boulmaiz, T., Quast, R., & Vreugdenhill, M. (2025). Investigating hydrological modeling uncertainties in the Mediterranean by combining precipitation and soil moisture products. Journal of Hydrology: Regional Studies, 62, 103015. doi:10.1016/j.ejrh.2025.103015
- Singh, A., & Gaurav, K. (2023). Deep learning and data fusion to estimate surface soil moisture from multi-sensor satellite images. Scientific Reports, 13, 2251. doi:10.1038/s41598-023-28939-9
- Settu, P., & Ramaiah, M. (2025). A data driven comparison of hybrid machine learning techniques for soil moisture modeling using remote sensing imagery. Scientific Reports, 15, 43170. doi:10.1038/s41598-025-27225-0
- Wei, Z., Wei, L., Wang, T., Lu, Q., Tian, S., Zhang, F., & Zhong, Y. (2025). A global long-term daily multilayer soil moisture dataset derived from machine learning. Scientific Data, 13, 122. doi:10.1038/s41597-025-06436-0
- Zhang, C., & Yao, Y. (2023). Basin-scale soil moisture assimilation and its hydrological impacts using an ensemble Kalman filter. Advances in Water Resources, 158, 104065. doi:10.1016/j.advwatres.2021.104065 (Note: example foundational source)
- Global soil moisture data derived through machine learning trained with in-situ measurements. Scientific Data. Available at: https://www.nature.com/articles/s41597-021-00964-1
- Soil Moisture Prediction Using Remote Sensing and Machine Learning Algorithms: A Review on Progress, Challenges, and Opportunities. Remote Sensing (MDPI). Available at: https://www.mdpi.com/2072-4292/17/14/2397
- Deep learning and data fusion to estimate surface soil moisture from multi-sensor satellite images. Scientific Reports. Available at: https://www.nature.com/articles/s41598-023-28939-9
- Enhancing assimilated soil moisture prediction from environmental data using advanced machine learning. Environmental Systems Research. Available at: https://link.springer.com/article/10.1186/s40068-025-00451-1
- A global long-term daily multilayer soil moisture dataset derived from machine learning. Scientific Data. Available at: https://www.nature.com/articles/s41597-025-06436-0
- Regional Soil Moisture Estimation Leveraging Multi-Source Data Fusion and Automated Machine Learning. Remote Sensing (MDPI). Available at: https://www.mdpi.com/2072-4292/17/5/837
- A data driven comparison of hybrid machine learning techniques for soil moisture modeling using remote sensing imagery. Scientific Reports. Available at: https://www.nature.com/articles/s41598-025-27225-0
- Machine learning approaches for soil moisture prediction: enhancing agricultural water management with integrated data. Modeling Earth Systems and Environment. Available at: https://link.springer.com/article/10.1007/s40808-025-02607-5
- Integrated framework for hydrologic modelling in data-sparse watersheds and climate change impact on projected green and blue water sustainability. Frontiers in Environmental Science. Available at: https://www.frontiersin.org/journals/environmental-science/articles/10.3389/fenvs.2023.1233216/full
- Machine learning for soil moisture analysis: a survey and emerging perspectives. International Journal of Data Science and Analytics. Available at: https://link.springer.com/article/10.1007/s41060-025-00977-8
- Global long term daily 1 km surface soil moisture dataset with physics informed machine learning. Scientific Data. Available at: https://www.nature.com/articles/s41597-023-02011-7
- Investigating hydrological modeling uncertainties in the Mediterranean region by combining precipitation and soil moisture products. ScienceDirect. Available at: https://www.sciencedirect.com/science/article/pii/S2214581825008444
- Hydrology and Earth System Sciences preprint: Soil moisture modelling study. Available at: https://hess.copernicus.org/preprints/hess-2020-302/hess-2020-302-manuscript-version4.pdf