Prediksi ISPU Jakarta Menggunakan Random Forest

Renaldi Putra Roris; Andhika Saputra; Ahmad Fahrizal; Susi Susilowati; Harsih Rianto; Yamin Nuryamin

doi:10.47134/jacis.v5i2.139

Authors

Renaldi Putra Roris Universitas Bina Sarana Informatika
Andhika Saputra Universitas Bina Sarana Informatika
Ahmad Fahrizal Universitas Bina Sarana Informatika
Susi Susilowati Universitas Bina Sarana Informatika
Harsih Rianto Universitas Bina Sarana Informatika
Yamin Nuryamin Universitas Bina Sarana Informatika

DOI:

https://doi.org/10.47134/jacis.v5i2.139

Keywords:

Air Pollution Index (ISPU), air quality, machine learning, random forest, pollution prediction

Abstract

Polusi udara Jakarta memerlukan sistem prediksi akurat untuk peringatan dini kesehatan publik. Penelitian ini mengembangkan model machine learning untuk memprediksi Indeks Standar Pencemar Udara (ISPU) harian maksimum menggunakan dataset 3.045 observasi dari lima stasiun pemantauan (Januari–Agustus 2024) dengan enam parameter polutan (PM10, PM2.5, SO2, CO, O3, NO2). Tiga algoritma dievaluasi: Linear Regression, Random Forest, dan Gradient Boosting. Random Forest mencapai kinerja terbaik dengan R² = 0,9575, RMSE = 4,44, dan MAE = 0,82, melampaui studi sejenis (R² = 0,78–0,89). Analisis feature importance mengungkapkan PM2.5 mendominasi prediksi ISPU dengan kontribusi 87,11%, jauh melebihi NO2 (4,94%) dan SO2 (2,84%). Penelitian memberikan tiga kontribusi: (1) model prediksi ISPU akurasi tertinggi untuk implementasi sistem peringatan dini operasional; (2) identifikasi PM2.5 sebagai target prioritas kebijakan pengendalian polusi berbasis bukti; dan (3) bukti empiris bahwa polusi bersifat kronis dan menyeluruh, memerlukan intervensi komprehensif untuk melindungi kesehatan 10+ juta penduduk Jakarta

References

[1] World Health Organization, “WHO global air quality guidelines: Particulate matter (PM2.5 and PM10), ozone, nitrogen dioxide, sulfur dioxide and carbon monoxide,” 2021.

[2] G. Syuhada et al., “Impacts of air pollution on health and cost of illness in Jakarta, Indonesia,” Int. J. Environ. Res. Public Health, vol. 20, no. 4, p. 2916, 2023, doi: 10.3390/ijerph20042916. DOI: https://doi.org/10.3390/ijerph20042916

[3] Kementerian Lingkungan Hidup dan Kehutanan Republik Indonesia, “Peraturan Menteri Lingkungan Hidup dan Kehutanan tentang Indeks Standar Pencemar Udara,” 2020.

[4] M. Méndez, M. G. Merayo, and M. Núñez, “Machine learning algorithms to forecast air quality: A survey,” Artif. Intell. Rev., vol. 56, pp. 10031–10066, 2023, doi: 10.1007/s10462-023-10424-4. DOI: https://doi.org/10.1007/s10462-023-10424-4

[5] A. Kumar and P. Goyal, “Forecasting of daily air quality index in Delhi,” Sci. Total Environ., vol. 409, no. 24, pp. 5517–5523, 2011, doi: 10.1016/j.scitotenv.2011.08.069. DOI: https://doi.org/10.1016/j.scitotenv.2011.08.069

[6] J. J. Carbajal-Hernández, L. P. Sánchez-Fernández, J. A. Carrasco-Ochoa, and J. F. Martínez-Trinidad, “Assessment and prediction of air quality using fuzzy logic and autoregressive models,” Atmos. Environ., vol. 60, pp. 37–50, 2012, doi: 10.1016/j.atmosenv.2012.06.001. DOI: https://doi.org/10.1016/j.atmosenv.2012.06.004

[7] X. Li et al., “Long short-term memory neural network for air pollutant concentration predictions: Method development and evaluation,” Environ. Pollut., vol. 231, pp. 997–1004, 2017, doi: 10.1016/j.envpol.2017.08.114. DOI: https://doi.org/10.1016/j.envpol.2017.08.114

[8] N. Gupta, S. Gupta, M. Khosravy, N. Dey, and R. González-Crespo, “Prediction of air quality index using machine learning techniques: A comparative analysis,” J. Environ. Public Health, vol. 2023, p. 4916267, 2023, doi: 10.1155/2023/4916267. DOI: https://doi.org/10.1155/2023/4916267

[9] A. Houdou, I. Badisy, and K. Khomsi, “Interpretable machine learning approaches for forecasting and predicting air pollution: A systematic review,” Aerosol Air Qual. Res., vol. 24, no. 6, 2024, doi: 10.4209/aaqr.230394. DOI: https://doi.org/10.4209/aaqr.230151

[10] L. Breiman, “Random Forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324. DOI: https://doi.org/10.1023/A:1010933404324

[11] J. H. Friedman, “Greedy function approximation: A Gradient Boosting machine,” Ann. Stat., vol. 29, no. 5, pp. 1189–1232, 2001, doi: 10.1214/aos/1013203451. DOI: https://doi.org/10.1214/aos/1013203451

[12] F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011.

[13] I. M. Ihsan et al., “Air quality assessment based on real-time continuous monitoring: Particulate and nitrogen dioxide concentrations in South Tangerang,” J. Teknol. Lingkung., vol. 26, no. 1, pp. 97–104, 2025, doi: 10.55981/jtl.2025.2887.

[14] Scikit-learn Documentation, “Machine learning in Python.” 2024.