Machine Learning Estimation of Central Java Monthly Rainfall from Bias Corrected NASA POWER
DOI:
https://doi.org/10.21512/emacsjournal.v8i3.16835Keywords:
monthly rainfall estimation, NASA POWER, quantile mapping, XGBoost, random forestAbstract
Monthly rainfall underpins water availability, reservoir, and irrigation analyses, yet rain gauge records in Indonesia are sparse and often interrupted. This study compares multiple linear regression (MLR), eXtreme Gradient Boosting (XGBoost), and random forest (RF) for estimating monthly rainfall at nine stations in Central Java. NASA POWER daily rainfall was first bias-corrected at each station by fitting bin-wise linear equations between the gauge and satellite probability-duration curves, a piecewise form of empirical quantile mapping, using only data from before 2017. The corrected monthly series was the modeling target, and NASA POWER air temperature, relative humidity, and wind speed were the predictors; no rainfall variable was used as a predictor, although gauge information enters through the corrected target. The models were trained on a pooled sample of Java stations and verified against gauge observations from 2017–2019 and 2024–2026 at the same stations, so the verification is temporal only. The correction raised the mean monthly gauge–satellite correlation in the verification months from 0.81 to 0.84. On 178 station-months at six stations that were not used in training, the pooled RMSE was 126, 111, and 103 mm/month for MLR, XGBoost, and RF, equal to 69%, 61%, and 56% of the mean observed rainfall. Ensemble scores at three Semarang stations were optimistic because 108 of their verification months were also training months. The ensembles outperformed MLR, but the gap between XGBoost and RF was small and untested for significance. Independent and spatial validation is needed before operational use.
References
Aldrian, E., & Susanto, R. D. (2003). Identification of three dominant rainfall regions within Indonesia and their relationship to sea surface temperature. International Journal of Climatology, 23(12), 1435–1452. https://doi.org/10.1002/joc.950
Badan Meteorologi, Klimatologi, dan Geofisika. (2026a). Data Online BMKG [Data set]. Retrieved, from https://dataonline.bmkg.go.id/
Badan Meteorologi, Klimatologi, dan Geofisika. (2026b). Prediksi curah hujan kumulatif bulanan deterministik [Deterministic monthly cumulative rainfall prediction]. Retrieved October 27, 2026, from https://www.bmkg.go.id/iklim/prediksi-hujan-bulanan/curah-hujan-deterministik
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
Cahyono, C., Baria, A. B., Pierre, A. J., & Irawan, A. P. (2026). Statistical estimation of monthly rainfall in Jakarta, South Tangerang, and Bandung: A multiple linear regression baseline using BMKG station data. Engineering, Technology & Applied Science Research, 16(3), 36979–36985. https://doi.org/10.48084/etasr.19328
Cannon, A. J., Sobie, S. R., & Murdock, T. Q. (2015). Bias correction of GCM precipitation by quantile mapping: How well do methods preserve changes in quantiles and extremes? Journal of Climate, 28(17), 6938–6959. https://doi.org/10.1175/JCLI-D-14-00754.1
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). ACM. https://doi.org/10.1145/2939672.2939785
Ejike, O., Ndzi, D., & Shakir, M. Z. (2025). Comparative study of machine learning-based rainfall prediction in tropical and temperate climates. Climate, 13(8), Article 167. https://doi.org/10.3390/cli13080167
Gudmundsson, L., Bremnes, J. B., Haugen, J. E., & Engen-Skaugen, T. (2012). Technical note: Downscaling RCM precipitation to the station scale using statistical transformations – a comparison of methods. Hydrology and Earth System Sciences, 16(9), 3383–3390. https://doi.org/10.5194/hess-16-3383-2012
Hidayah, E., Halik, G., & Nusantara, W. (2024). Performance of GPM-IMERG satellite precipitation for rainfall-runoff modeling in Indonesia. Water Practice and Technology, 19(10), 3909–3928. https://doi.org/10.2166/wpt.2024.240
Jumadi, J., Danardono, D., Roziaty, E., Ulinuha, A., Supari, S., Choy, L. K., Sattar, F., & Nawaz, M. (2025). AI-driven ensemble learning for spatio-temporal rainfall prediction in the Bengawan Solo River watershed, Indonesia. Sustainability, 17(20), Article 9281. https://doi.org/10.3390/su17209281
Kashefi, M., Karami, H., Niksefat, M., & Ghazvinian, H. (2026). Prediction of monthly precipitation and maximum 24 h precipitation using random forest, decision tree and XGBoost models. Modeling Earth Systems and Environment, 12(1), Article 70. https://doi.org/10.1007/s40808-025-02714-3
Lavers, D. A., Simmons, A., Vamborg, F., & Rodwell, M. J. (2022). An evaluation of ERA5 precipitation for climate monitoring. Quarterly Journal of the Royal Meteorological Society, 148(748), 3152–3165. https://doi.org/10.1002/qj.4351
Lufira, R. D., Suhartanto, E., Andawayanti, U., Asmaranto, R., & Utami, R. T. (2026). A comparative assessment of advanced bias correction methods for GPM IMERG in Banjir Kanal Timur watershed. Engineering, Technology & Applied Science Research, 16(1), 32097–32103. https://doi.org/10.48084/etasr.15484
Moriasi, D. N., Arnold, J. G., Van Liew, M. W., Bingner, R. L., Harmel, R. D., & Veith, T. L. (2007). Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Transactions of the ASABE, 50(3), 885–900. https://doi.org/10.13031/2013.23153
NASA Langley Research Center. (2026). Prediction of Worldwide Energy Resources (POWER) daily point data, from https://power.larc.nasa.gov/
Nash, J. E., & Sutcliffe, J. V. (1970). River flow forecasting through conceptual models part I — A discussion of principles. Journal of Hydrology, 10(3), 282–290. https://doi.org/10.1016/0022-1694(70)90255-6
Ougahi, J. H., & Mahmood, S. A. (2022). Evaluation of satellite-based and reanalysis precipitation datasets by hydrologic simulation in the Chenab river basin. Journal of Water and Climate Change, 13(3), 1563–1582. https://doi.org/10.2166/wcc.2022.410
Papacharalampous, G., Tyralis, H., Doulamis, A., & Doulamis, N. (2023). Comparison of tree-based ensemble algorithms for merging satellite and earth-observed precipitation data at the daily time scale. Hydrology, 10(2), Article 50. https://doi.org/10.3390/hydrology10020050
Piñeiro, G., Perelman, S., Guerschman, J. P., & Paruelo, J. M. (2008). How to evaluate models: Observed vs. predicted or predicted vs. observed? Ecological Modelling, 216(3–4), 316–322. https://doi.org/10.1016/j.ecolmodel.2008.05.006
Ramadhan, R., Marzuki, M., Yusnaini, H., Muharsyah, R., Suryanto, W., Sholihun, S., Vonnisa, M., Battaglia, A., & Hashiguchi, H. (2022). Capability of GPM IMERG products for extreme precipitation analysis over the Indonesian Maritime Continent. Remote Sensing, 14(2), Article 412. https://doi.org/10.3390/rs14020412
Ramadhan, R., Marzuki, M., Yusnaini, H., Muharsyah, R., Tangang, F., Vonnisa, M., & Harmadi, H. (2023). A preliminary assessment of the GSMaP version 08 products over Indonesian Maritime Continent against gauge data. Remote Sensing, 15(4), Article 1115. https://doi.org/10.3390/rs15041115
Reichle, R. H., Liu, Q., Koster, R. D., Draper, C. S., Mahanama, S. P. P., & Partyka, G. S. (2017). Land surface precipitation in MERRA-2. Journal of Climate, 30(5), 1643–1664. https://doi.org/10.1175/JCLI-D-16-0570.1
Rodrigues, G. C., & Braga, R. P. (2021). Evaluation of NASA POWER reanalysis products to estimate daily weather variables in a hot summer Mediterranean climate. Agronomy, 11(6), Article 1207. https://doi.org/10.3390/agronomy11061207
Sabu, M. K. H., Yudianto, D., & Wijaya, O. T. (2025). Evaluasi curah hujan berbasis data global pada DAS Wae Mese, Labuan Bajo [Evaluation of global data-based rainfall in the Wae Mese watershed, Labuan Bajo]. Jurnal Sumber Daya Air, 21(1), 15–30. https://doi.org/10.32679/jsda.v21i1.906
Saleh, A., Tan, M. L., Yaseen, Z. M., & Zhang, F. (2024). Integrated machine learning models for enhancing tropical rainfall prediction using NASA POWER meteorological data. Journal of Water and Climate Change, 15(12), 6022–6042. https://doi.org/10.2166/wcc.2024.719
Sedghnejad, N., Nozari, H., & Marofi, S. (2024). Comparative analysis of classification techniques and input-output patterns for monthly rainfall prediction. Water Science, 38(1), 192–208. https://doi.org/10.1080/23570008.2024.2323879
Suhartanto, E., Andawayanti, U., Hidayat, M. N., Lufira, R. D., & Utami, R. T. (2025). A comparative evaluation of bias correction techniques for improving GPM-IMERG precipitation data in the Welang watershed, Indonesia. Engineering, Technology & Applied Science Research, 15(6), 29935–29941. https://doi.org/10.48084/etasr.13762
Suroso, S., Santoso, P. B., Birkinshaw, S., Kilsby, C., Bardossy, A., & Aldrian, E. (2023). Assessment of TRMM rainfall data for flood modeling in three contrasting catchments in Java, Indonesia. Journal of Hydroinformatics, 25(3), 797–814. https://doi.org/10.2166/hydro.2023.132
Tan, M. L., Armanuos, A. M., Ahmadianfar, I., Demir, V., Heddam, S., Al-Areeq, A. M., Abba, S. I., Halder, B., Kilinc, H. C., & Yaseen, Z. M. (2023). Evaluation of NASA POWER and ERA5-Land for estimating tropical precipitation and temperature extremes. Journal of Hydrology, 624, Article 129940. https://doi.org/10.1016/j.jhydrol.2023.129940
Themeßl, M. J., Gobiet, A., & Leuprecht, A. (2011). Empirical-statistical downscaling and error correction of daily precipitation from regional climate models. International Journal of Climatology, 31(10), 1530–1544. https://doi.org/10.1002/joc.2168
Tuasikal, H., Juwono, P. T., Sholichin, M., & Suhartanto, E. (2026). Evaluating linear scaling and random forest bias correction of GPM-IMERG V7 rainfall in Moluccas Islands watersheds. Engineering, Technology & Applied Science Research, 16(2), 34706–34711. https://doi.org/10.48084/etasr.17008
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Christian Cahyono, Denik Sri Krisnayanti, Dyah Erny Herwindiati, Juliastuti Juliastuti

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License - Share Alike that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
USER RIGHTS
All articles published Open Access will be immediately and permanently free for everyone to read and download. We are continuously working with our author communities to select the best choice of license options, currently being defined for this journal as follows: Creative Commons Attribution-Share Alike (CC BY-SA)


