Imputasi Curah Hujan ERA5 Menggunakan Random Forest dan XGBoost di Maluku Utara
DOI:
https://doi.org/10.35889/progresif.v22i3.3734Keywords:
ERA5, Imputasi, Statistical Downscaling, Random Forest, XGBoostAbstract
Climate change increases hydrometeorological disaster risks in North Maluku, yet missing BMKG rainfall data and ERA5's spatial bias hinder precise risk analysis. This study applied point-based Statistical Downscaling using Random Forest (RF) and Extreme Gradient Boosting (XGBoost), with ERA5 precipitation as the single predictor, to impute missing rainfall at four stations. XGBoost achieved lower MSE and RMSE at three stations (Sultan Babullah: MSE 1017.29, RMSE 31.89, MAE 12.31, R² 0.0351; Gamar Malamo: MSE 513.96, RMSE 22.67, MAE 9.91, R² -0.0141; Oesman Sadik: MSE 163.59, RMSE 12.79, MAE 6.27, R² 0.0369), with NRMSE-based accuracy of 83.89 – 87.56%, though RF retained slightly lower MAE. RF was selected at Emalamo (MSE 163.75, RMSE 12.79, MAE 5.62, R² -0.0517, accuracy 85.78%). The models imputed 298 missing days, though the univariate predictor underestimated rainfall above 40 mm. The resulting continuous dataset offers a scientific basis for regional disaster mitigation planning.
Key Word: ERA5; Imputation; Statistical Downscaling; Random Forest; XGBoost
Abstrak
Perubahan iklim meningkatkan risiko bencana hidrometeorologi di Maluku Utara, sementara kekosongan data curah hujan BMKG dan bias spasial ERA5 menghambat analisis risiko presisi. Penelitian ini menerapkan Statistical Downscaling berbasis titik menggunakan Random Forest (RF) dan Extreme Gradient Boosting (XGBoost), dengan presipitasi ERA5 sebagai prediktor tunggal, untuk mengimputasi kekosongan data curah hujan di empat stasiun. XGBoost menghasilkan MSE dan RMSE lebih rendah di tiga stasiun (Sultan Babullah: MSE 1017,29, RMSE 31,89, MAE 12,31, R² 0,0351; Gamar Malamo: MSE 513,96, RMSE 22,67, MAE 9,91, R² -0,0141; Oesman Sadik: MSE 163,59, RMSE 12,79, MAE 6,27, R² 0,0369), dengan akurasi berbasis NRMSE 83,89 – 87,56%, meski RF tetap mencatat MAE sedikit lebih rendah. RF terpilih di Emalamo (MSE 163,75, RMSE 12,79, MAE 5,62, R² -0,0517, akurasi 85,78%). Model berhasil mengimputasi 298 hari data kosong, meski prediktor univariat underestimate curah hujan di atas 40 mm. Basis data historis kontinu menjadi landasan saintifik bagi mitigasi bencana daerah.
References
[1] S. Suhadi, F. Mabruroh, A. Wiyanto, and I. Ikra, “Analisis Fenomena Perubahan Iklim Terhadap Curah Hujan Ekstrim,” Opt. J. Pendidik. Fis., vol. 7, no. 1, pp. 94–100, 2023, doi: 10.37478/optika.v7i1.2738.
[2] Mongabay, “Tragedi Banjir Bandang Ternate: Puluhan Korban Jiwa, Pencarian Masih Berlangsung,” Mongabay Indonesia. [Online]. Available: https://mongabay.co.id/2024/08/26/tragedi-banjir-bandang-ternate-puluhan-korban-jiwa-pencarian-masih-berlangsung/
[3] H. Hersbach et al., “The ERA5 global reanalysis,” Q. J. R. Meteorol. Soc., vol. 146, no. 730, pp. 1999–2049, 2020, doi: 10.1002/qj.3803.
[4] W. Hu, Y. Scholz, M. Yeligeti, L. von Bremen, and Y. Deng, “Downscaling ERA5 wind speed data: a machine learning approach considering topographic influences,” Environ. Res. Lett., vol. 18, no. 9, p. 094007, Sep. 2023, doi: 10.1088/1748-9326/aceb0a.
[5] A. Chakri et al., “Spatial Bias Correction of ERA5_Ag Reanalysis Precipitation Using Machine Learning Models in Semi-Arid Region of Morocco,” Atmosphere (Basel)., vol. 16, no. 11, pp. 1–35, 2025, doi: 10.3390/atmos16111234.
[6] R. Rahimi, H. Tavakol-Davani, and M. Nasseri, “An Uncertainty-Based Regional Comparative Analysis on the Performance of Different Bias Correction Methods in Statistical Downscaling of Precipitation,” Water Resour. Manag., vol. 35, no. 8, pp. 2503–2518, 2021, doi: 10.1007/s11269-021-02844-0.
[7] I. K. Sukhna, B. Miftahurrohmah, C. Wulandari, and P. Amelia, “Imputasi Data Temperatur Maksimum Menggunakan Metode Support Vector Regression,” JISKA (Jurnal Inform. Sunan Kalijaga), vol. 10, no. 2, pp. 171–185, 2025, doi: 10.14421/jiska.2025.10.2.171-185.
[8] A. Cahyaning, B. Miftahurrohmah, G. F. Prassida, and T. Tikno, “Filling the Precipitation Gaps: Accurate Imputation With Support Vector Regression in North Sulawesi,” Var. J. Stat. Its Appl., vol. 6, no. 2, pp. 183–194, 2024, doi: 10.30598/variancevol6iss2page183-194.
[9] B. Miftahurrohmah, H. Kuswanto, D. S. Pambudi, F. Fauzi, and F. Atmaja, “Assessment of the Support Vector Regression and Random Forest Algorithms in the Bias Correction Process on Temperatures,” Procedia Comput. Sci., vol. 234, pp. 637–644, 2024, doi: 10.1016/j.procs.2024.03.049.
[10] G. A. Mursianto, I. M. Falih, M. Irfan, T. Sakinah, and D. S. Prasvita, “Perbandingan Metode Klasifikasi Random Forest dan XGBoost Serta Implementasi Teknik SMOTE pada Kasus Prediksi Hujan,” J. Senamika, vol. 2, no. 2, pp. 41–50, 2021.
[11] R. U. Sibuea and H. Maulana, “Comparison of Random Forest and XGBOOST Methods on Weather in North Sumatera,” Tsabit J. Comput., vol. 2, no. 1, pp. 25–34, 2025, doi: 10.56211/tsabit44.
[12] D. Sangaji and T. Sutabri, “Analisis XGBoost dan Random Forest untuk Prediksi Curah Hujan dalam Mendukung Mitigasi Karhutla,” J. Pustaka AI (Pusat Akses Kaji. Teknol. Artif. Intell., vol. 5, no. 1, pp. 13–18, 2025, doi: 10.55382/jurnalpustakaai.v5i1.905.
[13] D. Kochkov et al., “Neural general circulation models for weather and climate,” Nature, vol. 632, no. 8027, pp. 1060–1066, 2024, doi: 10.1038/s41586-024-07744-y.
[14] H. Sun et al., “Corrected ERA5 Precipitation by Machine Learning Significantly Improved Flow Simulations for the Third Pole Basins,” J. Hydrometeorol., vol. 23, no. 10, pp. 1663–1679, 2022, doi: 10.1175/JHM-D-22-0015.1.
[15] J. Baño-Medina, R. Manzanas, and J. M. Gutierrez, “Configuration and intercomparison of deep learning neural models for statistical downscaling,” Geosci. Model Dev., vol. 13, no. 4, pp. 2109–2124, 2020, doi: 10.5194/gmd-13-2109-2020.
[16] B. Miftahurrohmah, I. A. Cholilie, S. U. Wijaya, F. Atmaja, T. Bariyah, and C. Wulandari, “Future Growing Seasons: Bias Correction with SVR and QDM for Indonesian Temperature Projection under RCP 2.6 and RCP 8.5,” vol. 2, no. 2, pp. 306–312, 2024, doi: https://doi.org/10.59796/jcst.V15N2.2025.100 Future.
[17] M. J. Rahaman, “A Comprehensive Review to Understand the Definitions, Advantages, Disadvantages and Applications of Machine Learning Algorithms,” Int. J. Comput. Appl., vol. 186, no. 31, pp. 43–47, 2024, doi: 10.5120/ijca2024923868.
[18] A. Syahreza, N. K. Ningrum, and M. A. Syahrazy, “Perbandingan Kinerja Model Prediksi Cuaca: Random Forest, Support Vector Regression, dan XGBoost,” Edumatic J. Pendidik. Inform., vol. 8, no. 2, pp. 526–534, 2024, doi: 10.29408/edumatic.v8i2.27640.
[19] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., vol. 13-17-Augu, pp. 785–794, 2016, doi: 10.1145/2939672.2939785.
[20] U. N. Christanto, B. Miftahurrohmah, T. Bariyah, H. Kuswanto, and N. Faria, “Cluster-Based Machine Learning Approaches for Predicting Daily Maximum Temperatures in Indonesia Under Climate Change,” JITK (Jurnal Ilmu Pengetah. dan Teknol. Komputer), vol. 11, no. 1, pp. 236–249, 2025, doi: 10.33480/jitk.v11i1.6749.
[21] F. Atmaja, B. Miftahurrohmah, I. A. Cholilie, S. U. Wijaya, N. Haliza, and Y. A. Utami, “Improving Agricultural Productivity in Indonesia Using Xgboost Precipitation Prediction with Downscaling and Bias Correction,” in 2024 7th International Conference on Informatics and Computational Sciences (ICICoS), IEEE, Jul. 2024, pp. 485–490. doi: 10.1109/ICICoS62600.2024.10636822.
[22] J. Vega-Durán, B. Escalante-Castro, F. A. Canales, G. J. Acuña, and B. Kaźmierczak, “Evaluation of Areal Monthly Average Precipitation Estimates from MERRA2 and ERA5 Reanalysis in a Colombian Caribbean Basin,” Atmosphere (Basel)., vol. 12, no. 11, p. 1430, Oct. 2021, doi: 10.3390/atmos12111430.
[23] Sartika Lina Mulani Sitio, Darmawati, and Yuda Samudra, “COMPARATIVE ANALYSIS OF BAGGING AND BOOSTING MODELS IN ENSEMBLE LEARNING FOR GRADUATION PREDICTION,” JITK (Jurnal Ilmu Pengetah. dan Teknol. Komputer), vol. 11, no. 3, pp. 979–986, Feb. 2026, doi: 10.33480/jitk.v11i3.7579.
[24] R. A. Hasyani, Y. M. Rangkuti, E. Simamora, S. Iskandar, and A. Idrus, “Extreme Gradient Boosting for Daily Rainfall Forecasting in Medan City,” JAIEA(Journal Artif. Intell. Eng. Appl., vol. 5, no. 2, pp. 3155–3163, 2026, doi: doi.org/10.59934/jaiea.v5i2.2136.
[25] A. Safril and A. Ulfiana, “Prediksi Curah Hujan Bulanan Menggunakan Metode Statistical Downscaling di Pulau Jawa dengan Pemilihan Prediktor Berdasarkan Transpor Uap Air,” J. Geogr., vol. 11, no. 1, pp. 19–33, Feb. 2019, doi: 10.24114/jg.v11i1.11474.
[26] B. K. Cahyono et al., “Leveraging machine learning and open accessed remote sensing data for precise rainfall forecasting,” Commun. Sci. Technol., vol. 10, no. 1, pp. 135–147, 2025, doi: 10.21924/cst.10.1.2025.1638.
