Perbandingan Kinerja Model Ensemble Learning untuk Prediksi Kejadian Hujan Esok Hari Berbasis Data Termodinamika BMKG
Abstract
Prediksi kejadian hujan harian merupakan komponen krusial dal vam sistem irigasi pertanian cerdas, namun ketersediaan variabel meteorologi dari sumber resmi yang terbatas menjadi tantangan utama. Penelitian ini mengusulkan sistem prediksi hujan esok hari menggunakan pendekatan ensemble learning berbasis data klimatologi harian SACA&D BMKG Stasiun Meteorologi Kemayoran periode 1993 hingga 2014 dengan total 8.035 observasi. Tiga fitur rekayasa dikonstruksi dari data suhu yaitu Temp_Range sebagai indikator termodinamika serta Day of Year dan Bulan sebagai representasi siklus monsun. Lima algoritma berbasis pohon keputusan dibandingkan dengan penanganan ketidakseimbangan kelas menggunakan pembobotan adaptif. Gradient Boosting terpilih sebagai model terbaik dengan AUC-ROC 0,7088 dan akurasi 66,89 persen setelah optimasi ambang batas klasifikasi. Studi ablasi menggunakan Time-Series Cross Validation lima lipatan membuktikan peningkatan AUC-ROC rata-rata sebesar 0,0754 secara konsisten lintas dekade. Dominasi Day of Year sebagai prediktor terkuat mengkonfirmasi peran pola monsun tahunan dalam menentukan kejadian hujan harian di Jakarta.
Keywords
Full Text:
PDFReferences
A. Sarasa-Cabezuelo, “Prediction of Rainfall in Australia Using Machine Learning,” Information, vol. 13, no. 4, hlm. 163, Mar 2022, doi: 10.3390/info13040163.
M. Del-Coco, M. Leo, dan P. Carcagnì, “Machine Learning for Smart Irrigation in Agriculture: How Far along Are We?,” Information, vol. 15, no. 6, hlm. 306, Mei 2024, doi: 10.3390/info15060306.
E. A. Abioye dkk., “Precision Irrigation Management Using Machine Learning and Digital Farming Solutions,” AgriEngineering, vol. 4, no. 1, hlm. 70–103, Feb 2022, doi: 10.3390/agriengineering4010006.
V. Krasnopolsky, “Applying Machine Learning in Numerical Weather and Climate Modeling Systems,” Climate, vol. 12, no. 6, hlm. 78, Mei 2024, doi: 10.3390/cli12060078.
J. M. Ahn, J. Kim, dan K. Kim, “Ensemble Machine Learning of Gradient Boosting (XGBoost, LightGBM, CatBoost) and Attention-Based CNN-LSTM for Harmful Algal Blooms Forecasting,” Toxins (Basel)., vol. 15, no. 10, hlm. 608, Okt 2023, doi: 10.3390/toxins15100608.
Bambang Setiyo Praytino dkk., “Daily dataset for climate extremes analyses in Southeast Asia,” SACA&D BMKG-KNMI. Diakses: 12 Juni 2026. [Daring]. Tersedia pada: https://sacad.bmkg.go.id/
E. J. M. van den Besselaar, G. van der Schrier, R. C. Cornes, A. S. Iqbal, dan A. M. G. Klein Tank, “SA-OBS: A Daily Gridded Surface Temperature and Precipitation Dataset for Southeast Asia,” J. Clim., vol. 30, no. 14, hlm. 5151–5165, Jul 2017, doi: 10.1175/JCLI-D-16-0575.1.
J. Cruz, M. Belo-Pereira, A. Fonseca, dan J. A. Santos, “Dynamic and Thermodynamic Drivers of Severe Sub-Hourly Precipitation Events in Mainland Portugal,” Atmosphere (Basel)., vol. 14, no. 9, hlm. 1443, Sep 2023, doi: 10.3390/atmos14091443.
J. An dkk., “Short-Term Heavy Rainfall Potential Identification Driven by Physical Features: Model Development and SHAP-Based Mechanism Interpretation,” Climate, vol. 14, no. 1, hlm. 24, Jan 2026, doi: 10.3390/cli14010024.
A. Mulsandi, Y. Koesmaryono, R. Hidayat, A. Faqih, dan A. Sopaheluwakan, “Detecting Indonesian Monsoon Signals and Related Features Using Space–Time Singular Value Decomposition (SVD),” Atmosphere (Basel)., vol. 15, no. 2, hlm. 187, Jan 2024, doi: 10.3390/atmos15020187.
M. Ariska, Suhadi, Supari, M. Irfan, dan I. Iskandar, “Spatio-Temporal Variations of Indonesian Rainfall and Their Links to Indo-Pacific Modes,” Atmosphere (Basel)., vol. 15, no. 9, hlm. 1036, Agu 2024, doi: 10.3390/atmos15091036.
H. Zhang, Y. Liu, C. Zhang, dan N. Li, “Machine Learning Methods for Weather Forecasting: A Survey,” Atmosphere (Basel)., vol. 16, no. 1, hlm. 82, Jan 2025, doi: 10.3390/atmos16010082.
L. Chen, B. Han, X. Wang, J. Zhao, W. Yang, dan Z. Yang, “Machine Learning Methods in Weather and Climate Applications: A Survey,” Applied Sciences, vol. 13, no. 21, hlm. 12019, Nov 2023, doi: 10.3390/app132112019.
L. Mdegela, E. Municio, Y. De Bock, E. Luhanga, J. Leo, dan E. Mannens, “Extreme Rainfall Event Classification Using Machine Learning for Kikuletwa River Floods,” Water (Basel)., vol. 15, no. 6, hlm. 1021, Mar 2023, doi: 10.3390/w15061021.
R. Szczepanek, “Daily Streamflow Forecasting in Mountainous Catchment Using XGBoost, LightGBM and CatBoost,” Hydrology, vol. 9, no. 12, hlm. 226, Des 2022, doi: 10.3390/hydrology9120226.
M. Putra, M. S. Rosid, dan D. Handoko, “High-Resolution Rainfall Estimation Using Ensemble Learning Techniques and Multisensor Data Integration,” Sensors, vol. 24, no. 15, hlm. 5030, Agu 2024, doi: 10.3390/s24155030.
M. Zambudio Martínez, L. H. M. da Silveira, R. Marin-Perez, dan A. F. S. Gomez, “Development and Comparison of Artificial Neural Networks and Gradient Boosting Regressors for Predicting Topsoil Moisture Using Forecast Data,” AI, vol. 6, no. 2, hlm. 41, Feb 2025, doi: 10.3390/ai6020041.
J.-Y. Chiang, Y. Lio, C.-Y. Hsu, C.-L. Ho, dan T.-R. Tsai, “Binary Classification with Imbalanced Data,” Entropy, vol. 26, no. 1, hlm. 15, Des 2023, doi: 10.3390/e26010015.
N. Bacanin, C. Stoean, M. Zivkovic, M. Rakic, R. Strulak-Wójcikiewicz, dan R. Stoean, “On the Benefits of Using Metaheuristics in the Hyperparameter Tuning of Deep Learning Models for Energy Load Forecasting,” Energies (Basel)., vol. 16, no. 3, hlm. 1434, Feb 2023, doi: 10.3390/en16031434.
R. S. Pontoh, T. Toharudin, B. N. Ruchjana, N. Sijabat, dan M. D. Puspita, “Bandung Rainfall Forecast and Its Relationship with Niño 3.4 Using Nonlinear Autoregressive Exogenous Neural Network,” Atmosphere (Basel)., vol. 13, no. 2, hlm. 302, Feb 2022, doi: 10.3390/atmos13020302.
O. Ejike, D. Ndzi, dan M. Z. Shakir, “Comparative Study of Machine Learning-Based Rainfall Prediction in Tropical and Temperate Climates,” Climate, vol. 13, no. 8, hlm. 167, Agu 2025, doi: 10.3390/cli13080167.
Refbacks
- There are currently no refbacks.
Editorial Office :
Prosiding SENDIKO (Seminar Nasional Hasil Penelitian & Pengabdian Masyarakat Bidang Ilmu Komputer)
Published by Universitas PGRI Madiun
Managed by Program Studi Sistem Informasi Fakultas Teknik Universitas PGRI Madiun
Address Jl. Auri 14-16 Kota Madiun Kampus III Universitas PGRI Madiun 63118
Website http://prosiding.unipma.ac.id/index.php/sendiko/index
Email [email protected]
e-ISSN: 3025-4604