Enhancing meteorological drought monitoring in arid regions: A machine learning-based fusion of satellite precipitation data

Document Type : Applied Article

Authors

Mahmoud Hajiani ¹

Mahsa Mardani ¹

Moein Tosan ²

¹ Department of Civil Engineering, Faculty of Engineering, University of Birjand, Birjand, Iran.

² Department of Irrigation and Reclamation Engineering, Faculty of Agriculture, University of Tehran, Karaj, Iran.

https://doi.org/10.22067/jwsd.v12i4.2511-1474

Abstract

Ensuring the accuracy of precipitation data in arid and semi-arid regions, which inherently face a scarcity of ground monitoring stations, is vital for sustainable water resource management and drought assessment. GPPs offer a promising alternative; however, they suffer from systematic biases and inherent uncertainties in estimating extreme values, limiting their direct application in hydrological models. This study aims to develop and evaluate a machine learning-based fusion model to generate a corrected daily precipitation product (ML-Corrected) and assess its efficacy in improving meteorological drought monitoring in South Khorasan Province, a representative arid and data-scarce region. To this end, four widely used GPPs were utilized alongside four spatiotemporal auxiliary variables (latitude, longitude, month, and day of year) as inputs for a RF model. Daily observational precipitation data from six synoptic stations (2010–2019) served as the target variable for model training and validation. Results indicated that the ML-Corrected product demonstrated absolute statistical superiority over all raw GPPs. In daily precipitation assessment, the ML-Corrected product achieved the highest correlation coefficient (median CC=0.87), the lowest error (median RMSE=0.78 mm/day), and the best success index (median CSI=0.545). More importantly, in drought monitoring assessment, the SPI time series derived from the ML-Corrected product (at both 3-month and 12-month scales) exhibited the highest agreement (median R2 > 0.81) and lowest error (median RMSE < 0.40) compared to observed SPI. These findings prove that the machine learning-based fusion approach acts as an intelligent error corrector, significantly reducing GPP uncertainty and providing a reliable precipitation dataset for water crisis management.

Keywords

Random forest

Standardized precipitation index (SPI)

Bias correction

Gridded precipitation products (GPPs)

Subjects

• Surface and Groundwater Resources

---

References

رضوانی مقدم، پ، کرباسی، ع، توسن، م، قراری، ف، فیضی، ح، و محتشمی، ت. (۱۳۹۵). زراعت و فناوری زعفران (Book of Abstracts: 2013-2016). زراعت و فناوری زعفران، ۴(ویژه‌نامه)، ۱-۷۸. https://doi.org/10.22048/jsat.2016.39250

توسن، م، خاشعی سیوکی، ع، سنگری، م، و رضوانی مقدم، پ. (۱۴۰۳). آنالیز روند جهانی تحقیقات زعفران (.Crocus sativus L) در بین سال‌های ۲۰۰۰ تا ۲۰۲۳. زراعت و فناوری زعفران، ۱۲ (۲)، ۱۱۵-۱۳۸. https://doi.org/10.22048/jsat.2024.443037.1524

Batista, F. F., Rodrigues, D. T., Santos e Silva, C. M., Andrade, L. d. M. B., Mutti, P. R., Potes, M., & Costa, M. J. (2025). Performance Assessment of IMERG V07 Versus V06 for Precipitation Estimation in the Parnaíba River Basin. Remote Sensing, 17(21), 3613. https://doi.org/10.3390/rs17213613

Bhaga, T. D., Dube, T., Shekede, M. D., & Shoko, C. (2020). Impacts of Climate Variability and Drought on Surface Water Resources in Sub-Saharan Africa Using Remote Sensing: A Review. Remote Sensing, 12(24), 4184. https://doi.org/10.3390/rs12244184

Bouaziz, M., Medhioub, E., & Csaplovisc, E. (2021). A machine learning model for drought tracking and forecasting using remote precipitation data and a standardized precipitation index from arid regions. Journal of Arid Environments, 189, 104478. https://doi.org/10.1016/j.jaridenv.2021.104478

Bui, H. T., Ishidaira, H., & Shaowei, N. (2019). Evaluation of the use of global satellite–gauge and satellite-only precipitation products in stream flow simulations. Applied Water Science, 9(3), 53. https://doi.org/10.1007/s13201-019-0931-y

Chen, J., Chen, K., & Zhu, Y. (2025). Hybrid CNN-LSTM-Attention Model for Enhanced Reference Crop Evapotranspiration Estimation toward Optimized Irrigation Scheduling. Journal of Agriculture and Food Research, 102545. https://doi.org/10.1016/j.jafr.2025.102545

Das, P., Zhang, Z., Ghosh, S., & Hang, R. (2024). A hybrid ensemble learning merging approach for enhancing the super drought computation over Lake Victoria Basin. Scientific Reports, 14(1), 13870. https://doi.org/10.1038/s41598-024-61520-6

Feizi, H., & Tosan, M. (2017). Saffron yield variability by climatic factors in the northeast of Iran. Acta Horticulturae. 1184, 109-114. https://doi.org/10.17660/ActaHortic.2017.1184.15

Feng, P., Wang, B., Liu, D. L., & Yu, Q. (2019). Machine learning-based integration of remotely-sensed drought factors can improve the estimation of agricultural drought in South-Eastern Australia. Agricultural Systems, 173, 303-316. https://doi.org/10.1016/j.agsy.2019.03.015

Ghosh, S., Lu, J., Das, P., & Zhang, Z. (2024). Machine learning algorithms for merging satellite-based precipitation products and their application on meteorological drought monitoring over Kenya. Climate Dynamics, 62(1), 141-163. https://doi.org/10.1007/s00382-023-06893-6

Hashemi, Z., Sodaeizadeh, H., Mokhtari, M. H., Ardakani, M. A. H., & Aliabadi, K. K. (2024). Monitoring and forecasting desertification and land degradation using remote sensing and machine learning techniques in Sistan plain, Iran. Journal of African Earth Sciences, 218, 105375. https://doi.org/10.1016/j.jafrearsci.2024.105375

Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Horányi, A., Muñoz‐Sabater, J., Nicolas, J., Peubey, C., Radu, R., & Schepers, D. (2020). The ERA5 global reanalysis. Quarterly journal of the royal meteorological society, 146(730), 1999-2049. https://doi.org/10.1002/qj.3803

Iqbal, Z., Shahid, S., Ahmed, K., Wang, X., Ismail, T., & Gabriel, H. F. (2022). Bias correction method of high-resolution satellite-based precipitation product for Peninsular Malaysia. Theoretical and Applied Climatology, 148(3), 1429-1446. https://doi.org/10.1007/s00704-022-04007-6

Kashani, A., & Safavi, H. R. (2025). Assessing groundwater drought in Iran using GRACE data and machine learning. Scientific Reports, 15(1), 14671. https://doi.org/10.1038/s41598-025-99342-9

Kossieris, P., Tsoukalas, I., Brocca, L., Mosaffa, H., Makropoulos, C., & Anghelea, A. (2024). Precipitation data merging via machine learning: Revisiting conceptual and technical aspects. Journal of Hydrology, 637, 131424. https://doi.org/10.1016/j.jhydrol.2024.131424

Lalmuanzuala, B., Sathyamoorthy, N., Dheebakaran, G., Jagadeeswaran, R., Ravikumar, R., & Sumathi, C. (2025). A comprehensive review of meteorological and remote sensing indices for drought monitoring and their in situ application in India. Environmental Reviews, 33, 1-15. https://doi.org/101139/er-2025-0077

Li, X., Jia, H., & Wang, L. (2023). Remote Sensing Monitoring of Drought in Southwest China Using Random Forest and eXtreme Gradient Boosting Methods. Remote Sensing, 15(19), 4840. https://doi.org/10.3390/rs15194840

Liu, Q., Li, Y., Yu, M., Chiu, L. S., Hao, X., Duffy, D. Q., & Yang, C. (2019). Daytime Rainy Cloud Detection and Convective Precipitation Delineation Based on a Deep Neural Network Method Using GOES-16 ABI Images. Remote Sensing, 11(21), 2555. https://doi.org/10.3390/rs11212555

Maggioni, V., Meyers, P. C., & Robinson, M. D. (2016). A Review of Merged High-Resolution Satellite Precipitation Product Accuracy during the Tropical Rainfall Measuring Mission (TRMM) Era. Journal of Hydrometeorology, 17(4), 1101-1117. https://doi.org/10.1175/JHM-D-15-0190.1

Mahmud, H. B., & Osawa, T. (2025). Analysis of the social impact of meteorological drought on Peninsular Malaysia based on the integration of precipitation satellites and sentiment analysis. International Journal of Disaster Risk Reduction, 119, 105314. https://doi.org/10.1016/j.ijdrr.2025.105314

Michibata, T. (2024). Radiative effects of precipitation on the global energy budget and Arctic amplification. npj Climate and Atmospheric Science, 7(1), 136. https://doi.org/10.1038/s41612-024-00684-4

Mwinjuma, M., Wang, R., Mtupili, M., & Twaha, M. (2026). Comparisons of SPI and SPEI in capturing drought dynamics: A Global assessment across arid and humid regions. Atmospheric Research, 329, 108475. https://doi.org/10.1016/j.atmosres.2025.108475

Negri, P., Acevedo, D., Ruiz, J., Gonzalez, S., Vidal, L., Silvarrey, A., & Nicora, M. G. (2025). Enhancing precipitation detection: A multi-sensor approach using conditional GANs and recurrent networks. Pattern Recognition Letters, https://doi.org/10.1016/j.patrec.2025.05.022

Nikoo, M. R., Tosan, M., Nazari, R., Vahabzadeh, M., Karimi, M., & Zarrinabadi, E. (2026). Assessing the fidelity of multi-satellite precipitation estimates for drought monitoring in a mountain water tower to arid basin system. Journal of Arid Environments, 232, 105519. https://doi.org/10.1016/j.jaridenv.2025.105519

Nourani, V., Tosan, M., Huang, J. J., Gebremichael, M., Kantoush, S. A., & Dastourani, M. (2025). Advances in multi-source data fusion for precipitation estimation: remote sensing and machine learning perspectives. Earth-Science Reviews, 270, 105253. https://doi.org/10.1016/j.earscirev.2025.105253

Oyarzabal, R. S., Santos, L. B. L., Cunningham, C., Broedel, E., de Lima, G. R. T., Cunha-Zeri, G., Peixoto, J. S., Anochi, J. A., Garcia, K., Costa, L. C. O., Pampuch, L. A., Cuartas, L. A., Zeri, M., Guedes, M. R. G., Negri, R. G., Muñoz, V. A., & Cunha, A. P. M. A. (2025). Forecasting drought using machine learning: a systematic literature review. Natural Hazards, 121, (8). 9823-9851. https://doi.org/10.1007/s11069-025-07195-2

Rahat, S. H., Saki, S., Khaira, U., Biswas, N. K., Dollan, I. J., Wasti, A., Miura, Y., Bhuiyan, M. A. E., & Ray, P. (2024). Bracing for impact: how shifting precipitation extremes may influence physical climate risks in an uncertain future. Scientific Reports, 14(1), 17398. https://doi.org/10.1038/s41598-024-65618-9

Raziei, T., & Pereira, L. S. (2024). Relating the Drought Precipitation Percentiles Index to the Standardized Precipitation Index (SPI) under Influence of Aridity and Timescale. Water Resources Management, 38(14), 5739-5758. https://doi.org/10.1007/s11269-024-03932-7

Rezaie-Balf, M., & Chua, L. H. C. (2025). An ensemble learning strategy for spatiotemporal drought assessment through the fusion of multi-satellite and atmospheric reanalysis precipitation products. Stochastic Environmental Research and Risk Assessment, 39(9), 3875-3901. https://doi.org/10.1007/s00477-025-03041-w

Sharma, T. C., & Panu, U. S. (2024). Current State of Advances in Quantification and Modeling of Hydrological Droughts. Water, 16(5), 729. https://doi.org/10.3390/w16050729

Shiru, M. S., Chung, E.-S., & Sa’adi, Z. (2025). Performance assessment of satellite precipitation products over Nigeria: A compromise programming approach. Earth Systems and Environment, 9(4), 3289-3310. https://doi.org/10.1007/s41748-024-00563-1

Tong, X., Zhou, W., & Xia, J. (2024). Improving Boreal Summer Precipitation Predictions From the Global NMME Through Res34‐Unet. Geophysical Research Letters, 51(2), e2023GL106391. https://doi.org/10.1029/2023GL106391

Tosan, M., Gharib, M. R., Mardani, M., & Sabbagh, A. (2026). Spatiotemporal performance and error analysis of satellite precipitation products over a topographically complex semi-arid region in Iran. Journal of Mountain Science, 23(1), 118-138. https://doi.org/10.1007/s11629-025-9984-6

Tosan, M., Nourani, V., Kisi, O., Zhang, Y., Kantoush, S.A. et al. (2026). The Transparency Revolution in Geohazard Science: A Systematic Review and Research Roadmap for Explainable Artificial Intelligence. Computer Modeling in Engineering & Sciences, 146(1), 3. https://doi.org/10.32604/cmes.2025.074768

Wu, X., Liu, Y., & Wang, R. (2025). Assessment of non-parametric method for evapotranspiration estimation across extreme conditions. Atmospheric Research, 326, 108279. https://doi.org/10.1016/j.atmosres.2025.108279

Zhang, Z., Wang, D., Qiu, J., Zhu, J., & Wang, T. (2021). Machine learning approaches for improving near-real-time IMERG rainfall estimates by integrating cloud properties from NOAA CDR PATMOS-x. Journal of Hydrometeorology, 22(10), 2767-2781. https://doi.org/10.1175/JHM-D-21-0019.1

Zhang, J., Ding, J., Wang, J., Lin, H., Han, L., Li, X., & Liu, J. (2023). Remote sensing drought factor integration based on machine learning can improve the estimation of drought in arid and semi-arid regions. Theoretical and Applied Climatology, 151(3), 1753-1770. https://doi.org/10.1007/s00704-022-04305-z

Zhang, X., Song, Y., Nam, W.-H., Huang, T., Gu, X., Zeng, J., Huang, S., Chen, N., Yan, Z., & Niyogi, D. (2024). Data fusion of satellite imagery and downscaling for generating highly fine-scale precipitation. Journal of Hydrology, 631, 130665. https://doi.org/10.1016/j.jhydrol.2024.130665

Zhu, H., Zhou, Q., & Cui, A. (2023). Comparison and evaluation of machine-learning-based spatial downscaling approaches on satellite-derived precipitation data. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences., X-1/W1-2023, 919-924. https://doi.org/10.5194/isprs-annals-X-1-W1-2023-919-2023