Stacking Ensemble Optimasi Genetic Algorithm Prediksi Indeks Standar Pencemar Udara Kota Jakarta
DOI:
https://doi.org/10.36277/jteuniba.v10i2.1364Keywords:
Prediksi ISPU, Stacking Ensemble, Genetic Algorithm, Deret Waktu, Kualitas UdaraAbstract
Kondisi kualitas udara di kota besar sering mengalami perubahan dari waktu ke waktu dan dapat berdampak pada lingkungan serta kesehatan masyarakat. Di Jakarta, informasi kualitas udara umumnya disajikan dalam bentuk Indeks Standar Pencemar Udara (ISPU), namun ketersediaan metode untuk memperkirakan kondisi kualitas udara di masa mendatang masih terbatas. Oleh karena itu penelitian ini mengusulkan pendekatan pemodelan prediksi untuk memperkirakan nilai ISPU harian menggunakan data deret waktu multivariat yang diperoleh dari stasiun pemantauan kualitas udara melalui portal Satu Data Jakarta. Model yang digunakan menerapkan arsitektur stacking ensemble yang menggabungkan RF dan XGB sebagai base learner serta Ridge Regression sebagai meta-learner. hyperparameter dilakukan menggunakan Genetic Algorithm untuk memperoleh konfigurasi parameter yang mampu meningkatkan kemampuan pembelajaran model. Evaluasi dilakukan menggunakan skema walk-forward recursive forecasting berbasis TimeSeriesSplit dengan metrik penilaian RMSE, MAE, MAPE, dan R². Hasil eksperimen menunjukkan bahwa model stacking ensemble yang dioptimasi dengan Genetic Algorithm menghasilkan performa terbaik dengan RMSE sebesar 1.9802 dan R² sebesar 0.9902 sehingga pendekatan ini mampu meningkatkan akurasi prediksi pada data deret waktu ISPU.
Downloads
References
REFERENSI
K. Muhamad, L. Puji, D. Oktavia, D. Pratiwi, Y. Uchiyama, and D. Harding, “Towards blue skies : A comprehensive review and regional mapping of ambient air quality in Indonesian cities,” J. Environ. Manage., vol. 389, no. September 2024, p. 126132, 2025, doi: 10.1016/j.jenvman.2025.126132.
A. Pratama, C. Gudiato, A. Maulana, and W. Prayitno, “Prediksi ISPU Berbasis SVM untuk Masa Depan Jakarta yang Berkelanjutan SVM-Driven ISPU Prediction for Jakarta ’ s Sustainable Future,” vol. 15, no. 1, pp. 66–76, 2025.
M. Kusnandar, “Permen LHK Nomor 14 Tahun 2020,” Permen LHK Nomor 14 Tahun 2020 Tentang Indeks Standar Pencemar Udar., pp. 1–16, 2020, [Online]. Available: https://jdih.menlhk.go.id/new2/uploads/files/P_14_2020_ISPU_menlhk_07302020074834.pdf
D. K. Nurlaili and N. Hendrasarie, “Analisa Kualitas Lingkungan Udara Ambien ( PM2 . 5 ) di Kota Surabaya,” vol. IX, no. 1, pp. 7978–7985, 2024.
Z. Yang, R. Mahendran, P. Yu, R. Xu, W. Yu, and S. Godellawattage, “Health Effects of Long ‑ Term Exposure to Ambient PM 2 . 5 in Asia ‑ Pacific : a Systematic Review of Cohort Studies,” Curr. Environ. Heal. Reports, pp. 130–151, 2022, doi: 10.1007/s40572-022-00344-w.
C. Muluken, E. Di, S. Ferraris, and R. Meo, “Machine Learning with Applications Hyperparameter optimization of machine learning models for predicting actual evapotranspiration,” Mach. Learn. with Appl., vol. 20, no. January, p. 100661, 2025, doi: 10.1016/j.mlwa.2025.100661.
V. Nedungadi et al., “Through Multi-Variable Data Alignment,” 2024.
G. Ravindiran, G. Hayder, K. Kanagarathinam, A. Alagumalai, and C. Sonne, “Air quality prediction by machine learning models: A predictive study on the indian coastal city of Visakhapatnam,” Chemosphere, vol. 338, no. May, p. 139518, 2023, doi: 10.1016/j.chemosphere.2023.139518.
A. Ksibi, A. Salhi, A. S. Alluhaidan, and S. A. El-rahman, “Airstacknet : A Stacking Ensemble-Based Approach for Air Quality Prediction,” 2023, doi: 10.32604/cmc.2023.032566.
Z. Xu, H. Zhang, A. Zhai, C. Kong, and J. Zhang, “Stacking Ensemble Learning and SHAP-Based Insights for Urban Air Quality Forecasting: Evidence from Shenyang and Global Implications,” Atmosphere (Basel)., vol. 16, no. 7, pp. 1–22, 2025, doi: 10.3390/atmos16070776.
T. A. Munshi, K. Popi, L. N. Jahan, M. F. Howladar, and M. Hashan, “Applied Computing and Geosciences Stacking modeling with genetic algorithm-based hyperparameter tuning for uniaxial compressive strength prediction,” Appl. Comput. Geosci., vol. 27, no. February, p. 100276, 2025, doi: 10.1016/j.acags.2025.100276.
H. Alibrahim and S. A. Ludwig, “Hyperparameter Optimization : Comparing Genetic Algorithm against Grid Search and Bayesian Optimization”.
J. D. S. Kumar, P. Rizwana, M. Pushpanjali, Y. S. Mallika, P. A. Sree, and T. Meghana, “RESEARCH IN ENGINEERING MANAGEMENT AIR QUALITY INDEX FORECASTING VIA GENETIC ALGORITHM BASED IMPROVED EXTREME LEARNING MACHINE,” pp. 1784–1790, 2024.
H. Wu, J. Xu, J. Wang, and M. Long, “Autoformer : Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting,” no. NeurIPS, 2021.
U. A. Yakubu, M. Panji, and A. Saputra, “Time Series Model Analysis Using ( ACF ) and ( PACF ) for E-wallet Transactions during a Pandemic,” vol. 3, no. 3, pp. 80–85, 2022.
A. Abdul, M. Yusoff, W. Fairos, W. Yaacob, and Z. Mustaffa, “MethodsX Repeated time-series cross-validation : A new method to improved COVID-19 forecast accuracy in Malaysia,” vol. 13, no. August, 2024, doi: 10.1016/j.mex.2024.103013.
X. Huang et al., “A Hybrid ARIMA-LSTM-XGB Model with Linear Regression Stacking for Transformer Oil Temperature Prediction,” pp. 1–21, 2025.
T. A. Munshi, K. Popi, L. N. Jahan, M. F. Howladar, and M. Hashan, “Applied Computing and Geosciences Stacking modeling with genetic algorithm-based hyperparameter tuning for uniaxial compressive strength prediction,” Appl. Comput. Geosci., vol. 27, no. August, p. 100276, 2025, doi: 10.1016/j.acags.2025.100276.
K. Al-saeedi, D. Zhou, A. Fish, K. Tsakiri, and A. Marsellos, “A Methodological Comparison of Forecasting Models Using KZ Decomposition and Walk-Forward Validation,” pp. 1–25, 2025.
M. J. Diamantopoulou and R. Ozçelik, “Evaluation of the RFregression machine learning technique as an alternative to ecoregional based regression taper modelling,” vol. 239, no. August, 2025.
D. Tarwidi, S. Redjeki, D. Adytia, and M. Apri, “MethodsX An optimized XGB-based machine learning method for predicting wave run-up on a sloping beach,” MethodsX, vol. 10, no. December 2022, p. 102119, 2023, doi: 10.1016/j.mex.2023.102119.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Fahmi Hammam Taqiyuddin, Aviolla Terza Damaliana, Andri Fauzan Adziima
This work is licensed under a Creative Commons Attribution 4.0 International License.
