Prediksi Particulate Matter (PM 2.5) di DKI Jakarta Menggunakan XGBoost
DOI:
https://doi.org/10.36754/jam.v2i1.355Keywords:
PM2.5, Kualitas Udara, XGBoost, Prediksi, JakartaAbstract
Dalam dekade terakhir, kualitas udara di kota-kota besar, seperti Jakarta, telah menjadi pusat perhatian yang serius karena implikasinya terhadap kesehatan dan lingkungan. Salah satu parameter penting dalam penilaian kualitas udara adalah konsentrasi Particulate Matter (PM) dengan diameter kurang dari atau sama dengan 2.5 mikrometer (PM2.5). Studi ini bertujuan untuk mengembangkan model prediktif menggunakan Extreme Gradient Boosting (XGBoost) untuk memprediksi tingkat PM2.5 di Jakarta. XGBoost dipilih karena keunggulan performanya dalam menangani data non-linier dan besar, serta kemampuannya dalam menangani missing values yang sering terjadi dalam data lingkungan. Model dikembangkan dengan menggunakan dataset yang mencakup data historis PM2.5 yang dikumpulkan dari stasiun pemantauan di Jakarta. Kinerja model dievaluasi menggunakan metrik seperti Root Mean Square Error (RMSE) sebesar 16.77, Mean Absolute Error (MAE) sebesar 11.39, dan R-squared (R²) sebesar 0.6812. Hasil awal menunjukkan bahwa model XGBoost dapat secara baik memprediksi konsentrasi PM2.5 di Jakarta
References
World Health Organization (WHO). (2021). Air quality guidelines – Global update 2021. Retrieved from WHO website: https://www.who.int/publications/i/item/9789240034228
Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785-794). ACM.
Zhang, H., Wang, Y., Hu, J., Ying, Q., & Hu, X. M. (2015). Relationships between meteorological parameters and criteria air pollutants in three megacities in China. Environmental Research, 140, 242-254. DOI:10.1016/j.envres
Kim, J. H., Kim, H., & Lim, S. C. (2019). The complex relationship between air pollution and health in Asian cities: A review of the challenges and opportunities. Environmental Science & Policy, 93, 295-307.
Pope III, C. A., & Dockery, D. W. (2006). Health effects of fine particulate air pollution: lines that connect. Journal of the Air & Waste Management Association, 56(6), 709-742.
Kurniawan, J., & Khardi, S. (2020). Assessment of air pollution impacts on public health in the urban area of Jakarta, Indonesia. Environmental Monitoring and Assessment, 192(4), 245.
Ni, Z., Liu, F., Shu, L., & Wang, Y. (2019). Prediction of PM2.5 concentrations based on improved XGBoost model. In 2019 IEEE 3rd International Conference on Energy Internet (ICEI) (pp. 486-491). IEEE.
Li, X., Peng, L., Yao, X., Cui, S., Hu, Y., You, C., & Chi, T. (2016). Long short-term memory neural network for air pollutant concentration predictions: Method development and evaluation. Environmental Pollution, 231, 997-1004.
Lee, H., Liu, Y., Coull, B. A., Schwartz, J., & Koutrakis, P. (2017). A novel calibration approach of MODIS AOD data to predict PM2.5 concentrations. Atmospheric Chemistry and Physics, 17(15), 9595-9611.
Zhang, L., Wang, B., Dawson, J. W., & Harrington, J. Y. (2019). The role of aerosols in precipitation processes: A review. Atmospheric Research, 227, 183-195.
Liang, X., Li, S., Zhang, S., Huang, H., & Chen, S. X. (2016). PM2.5 data reliability, consistency, and air.
Septiadi, D., Saputra, A. H., Virgianto, R. H., Yuniarto, A., & Yuggotomo, M. E. (2023). THE ANALYSIS OF LAPSE RATE PROFILE IN THE SITE CANDIDATE OF NUCLEAR POWER PLANT (NPP) AT GOSONG BEACH, BENGKAYANG REGENCY–WEST KALIMANTAN. Jurnal Sains dan Teknologi Nuklir Indonesia (Indonesian Journal of Nuclear Science and Technology), 23(1), 23-31.
Virgianto, R. H., Rivaniputra, R., Kinanti, N. P., Saputra, A. H., & Khoir, A. N. (2022). A numerical simulation of PM2. 5 concentration using the WRF-Chem model during a high air pollution episode in 2019 in Jakarta, Indonesia. Int J Adv Appl Sci, 11(4), 335-344.
Saputra, A. H., Lukita, N. R., & Oktarina, S. (2022). Pengaruh Teknik Asimilasi Penakar Hujan Brandes Spatial Adjustment terhadap Quantitative Precipitation Estimation (QPE) Radar BMKG Padang. Jurnal Fisika Unand, 11(3), 373-379.
Saputra, A. H., Muchtar, R. M., & Oktarina, S. (2022). Pengaruh Asimilasi Data Radiance Satelit pada Model WRF (Weather Research and Forecasting) untuk Prediksi Siklon Tropis Frances. Jurnal Aplikasi Meteorologi, 1(1), 8-18.
Sagita, N., Saputra, A. H., & Novianti, R. (2022). Identification of Dominant Factor for Air Pollution Fluctuations at The Beginning of Covid-19 Large-Scale Social Restrictions (PSBB) in Jakarta. Jurnal EnviScience (Environment Science), 6(1), 31-44.
Sihombing, C., Saputra, A. H., Sari, F. P., & Mulya, A. (2022). Prediksi Curah Hujan di Wilayah DKI Jakarta dengan Model NeuralProphet. Jurnal Aplikasi Meteorologi, 1(2).
Saputra, A. H., & Oktarina, S. (2022). Comparing the Performance of Three Decision Tree Models for Precipitation Prediction in Cengkareng Soekarno Hatta. Jurnal Aplikasi Meteorologi, 1(2).
Giarno, G., Saputra, A. H., & Rachmawardani, A. (2022). Optimalisasi Edukasi Informasi Geohidrometeorologi Untuk Masyarakat Perkotaan (Studi Kasus: Kelurahan Jurang Mangu Timur, Kecamatan Pondok Aren, Kota Tangerang Selatan, Banten). To Maega: Jurnal Pengabdian Masyarakat, 5(3), 554-563.
Paksi, L. M. W., Saputra, A. H., & Fitrianti, I. (2021, November). Eight scenarios rapid update cycle effect on weather radar data assimilation WRF toward rainfall prediction in Palembang (cases study of flood events on November 12th, 2018). In IOP Conference Series: Earth and Environmental Science (Vol. 893, No. 1, p. 012038). IOP Publishing.
