DOI: https://doi.org/10.14710/j.gauss.15.1.98-109

PREDIKSI KEKERINGAN DENGAN MENGGUNAKAN RANDOM FOREST DAN XGBOOST SEBAGAI STRATEGI MITIGASI BENCANA DI KABUPATEN MAJENE

*Muh. Hijrah orcid  -  Universitas Sulawesi Barat, Indonesia
Putri Indi Rahayu  -  Program Studi Statistika, Universitas Sulawesi Barat, Indonesia
Wahyudi Wahyudi  -  Program Studi Statistika, Universitas Sulawesi Barat, Indonesia
Open Access Copyright 2026 Jurnal Gaussian under http://creativecommons.org/licenses/by-nc-sa/4.0.

Citation Format:
Abstract
The growing incidence of drought attributable to climate change poses serious challenges to food systems and agricultural livelihoods in Majene Regency, West Sulawesi. To address this, the present study compares the predictive accuracy of Random Forest and XGBoost in classifying drought occurrences from meteorological variables, using 300 monthly observations recorded by BMKG between 2000 and 2024. Exploratory data analysis revealed that 60% of drought events are concentrated in August and the target variable is severely imbalanced (16.3% drought vs. 83.7% non-drought). At the default threshold of 0.50, Random Forest outperforms XGBoost in all metrics. However, because imbalanced data causes both models to underdetect drought at the default threshold (sensitivity = 0.267), threshold optimization was applied by lowering the decision threshold to τ = 0.15. The result of threshold optimalization was significantly improved Random Forest sensitivity from 0.267 to 0.867, detecting 13 out of 15 drought events in the test set while maintaining an AUC-ROC of 0.916. Feature importance analysis consistently identifies X3 as the dominant predictor in both models. Random Forest with threshold τ = 0.15 is recommended as the primary model for drought early warning systems in Majene.

Note: This article has supplementary file(s).

Fulltext View|Download |  common.other
Drought Prediction Using Random Forest and XGBoost as a Disaster Mitigation Strategy in Majene Regency
Subject Artikel Fix
Type Other
  Download (5MB)    Indexing metadata
Email colleagues
Keywords: Drought; Weather; Machine Learning; Random Forest; XGBoost

Article Metrics:

Article Info
Section: Articles
Language : ID
  1. Ainurrohmah, S. & Sudarti, S. 2022. Analisis Perubahan Iklim dan Global Warming yang Terjadi sebagai Fase Kritis. Jurnal Phi: Jurnal Pendidikan Fisika dan Fisika Terapan, 8(1), hlm. 1–10
  2. Breiman, L. 2001. Random Forests. Machine Learning, 45(1), hlm. 5–32. doi: 10.1023/A:1010933404324
  3. Chen, T. & Guestrin, C. 2016. XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, hlm. 785–794. doi: 10.1145/2939672.2939785
  4. Cholissodin, I., Sutrisno, Soebroto, A. A., Hasanah, U. & Febiola, Y. I. 2020. AI, Machine Learning & Deep Learning (Teori & Implementasi). Malang: FILKOM UB
  5. Dwiyanti, Z.A. & Prianto, C. 2023. Prediksi Cuaca Kota Jakarta Menggunakan Metode Random Forest. Jurnal Tekno Insentif, 17(2), hlm. 127–137
  6. Ehteram, M. & Shabanian, H. 2023. Unveiling the SALSTM-M5T Model and Its Python Implementation for Precise Solar Radiation Prediction. Energy Reports, 10, hlm. 3402–3417
  7. Elkan, C. 2001. The Foundations of Cost-Sensitive Learning. Proceedings of the 17th International Joint Conference on Artificial Intelligence (IJCAI), hlm. 973–978
  8. Hafdz, D., Wardhana, A. & Prawira, M.R. 2023. The Analysis of Indonesia’s Climate Change Policies in Response to the 2021 IPCC Assessment Report. Jurnal Internasional Ilmu Politik dan Hubungan Internasional, 1, hlm. 42–53
  9. Hanley, J.A. & McNeil, B.J. 1982. The Meaning and Use of the Area under a Receiver Operating Characteristic (ROC) Curve. Radiology, 143(1), hlm. 29–36
  10. Hastie, T., Tibshirani, R. & Friedman, J. 2009. The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2nd ed.). New York: Springer
  11. He, H. & Garcia, E.A. 2009. Learning from Imbalanced Data. IEEE Transactions on Knowledge and Data Engineering, 21(9), hlm. 1263–1284
  12. Lestari, E.S. & Astuti, I. 2022. Penerapan Random Forest Regression untuk Memprediksi Harga Jual Rumah. Jurnal Ilmiah FIFO, 14(2), hlm. 131. doi: 10.22441/fifo.2022.v14i2.003
  13. McKee, T.B., Doesken, N.J. & Kleist, J. 1993. The Relationship of Drought Frequency and Duration to Time Scales. Proceedings of the 8th Conference on Applied Climatology, hlm. 179–183
  14. Neya, T. et al. 2024. Climate Change Impact Assessment and Disaster Risk Financing Strategies in Mali. International Journal of Environment and Climate Change, 14(3), hlm. 126–138
  15. Nugraha, A.C. & Irawan, M.I. 2023. Komparasi Deteksi Kecurangan pada Data Klaim Asuransi Menggunakan SVM dan XGBoost. Jurnal Sains dan Seni ITS, 12(1). doi: 10.12962/j23373520.v12i1.107032
  16. Powers, D.M.W. 2020. Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness and Correlation. Journal of Machine Learning Technologies, 2(1), hlm. 37–63
  17. Prasetya, E.P. & Djamal, E.C. 2019. Rainfall Forecasting for the Natural Disasters Preparation Using Recurrent Neural Networks. Proceedings of the International Conference on Electrical Engineering and Informatics (ICEEI), hlm. 52–57
  18. Sokolova, M. & Lapalme, G. 2009. A Systematic Analysis of Performance Measures for Classification Tasks. Information Processing & Management, 45(4), hlm. 427–437
  19. Zhang, P., Jia, Y. & Shang, Y. 2022. Research and Application of XGBoost in Imbalanced Data. International Journal of Distributed Sensor Networks, 18(6). doi: 10.1177/15501329221106935

Last update:

No citation recorded.

Last update:

No citation recorded.