Bias Correction of Satellite Precipitation Products Near the Data-Scarce Region of Al-Ahsa, Saudi Arabia

A novel bias correction algorithm using machine learning models effectively improves the accuracy of satellite precipitation products in arid regions, such as Al-Ahsa Oasis in Saudi Arabia. The study found that a one-dimensional ConvLSTM model outperformed Random Forest and XGBoost, reducing relative bias from 50.8% to -1.71% for CMORPH and from 282.2% to +1.15% for IMERG datasets. This approach is particularly suitable for regions with limited topographical variation and prominent temporal variability, offering a valuable tool for sustainable water resource management, agricultural planning, and drought mitigation in data-scarce arid areas.

Abdullah, M., & Al-Areeq, A. M. (2026). Bias Correction of Satellite Precipitation Products Near the Data-Scarce Region of Al-Ahsa, Saudi Arabia. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 19, 22685–22694. https://doi.org/10.1109/jstars.2026.3708749