PREDIKSI KUALITAS UDARA MENGGUNAKAN LONG SHORT-TERM MEMORY (LSTM) DI DAERAH ISTIMEWA YOGYAKARTA
Keywords:
PM, Kualitas Udara, LSTM, Random Forest, XGBoostAbstract
Pencemaran udara, khususnya PM₂.₅, menjadi permasalahan lingkungan serius di Daerah Istimewa Yogyakarta akibat pertumbuhan penduduk, peningkatan aktivitas transportasi, serta pengaruh aktivitas vulkanik Gunung Merapi. Konsentrasi PM₂.₅ di wilayah perkotaan dilaporkan telah melampaui baku mutu nasional dan pedoman internasional, sehingga diperlukan metode prediksi yang andal untuk mendukung pengendalian kualitas udara. Penelitian ini bertujuan menganalisis kinerja model LSTM dalam memprediksi konsentrasi PM₂.₅ berbasis multivariate time-series serta membandingkannya dengan Random Forest dan XGBoost. Data yang digunakan berupa data harian konsentrasi polutan udara (CO, NO₂, O₃, PM₁₀, PM₂.₅, dan SO₂) pada periode 1 Januari 2020 hingga 31 Desember 2024. Tahapan preprocessing meliputi penanganan missing values menggunakan MICE dan normalisasi fitur dengan Min-Max Normalization. Evaluasi model dilakukan menggunakan MAE, RMSE, dan R². Hasil penelitian menunjukkan bahwa XGBoost memberikan performa terbaik dengan RMSE 38,58 µg/m³ dan R² 0,81, sedangkan LSTM menunjukkan performa kompetitif dengan MAE 21,00 µg/m³ serta lebih efektif dalam menangkap pola temporal jangka panjang. Random Forest menghasilkan performa terendah dengan nilai R² negatif. Secara keseluruhan, penelitian ini menunjukkan bahwa pendekatan deep learning dan boosting lebih efektif untuk pemodelan time-series kualitas udara.
References
BMKG. (2024). Laporan kualitas udara dan parameter meteorologi Indonesia tahun 2024. Badan Meteorologi, Klimatologi, dan Geofisika.
Brook, R. D., Rajagopalan, S., Pope, C. A., III, Brook, J. R., Bhatnagar, A., Diez-Roux, A. V., … Kaufman, J. D. (2010). Particulate matter air pollution and cardiovascular disease: An update to the scientific statement from the American Heart Association. Circulation, 121(21), 2331–2378. https://doi.org/10.1161/CIR.0b013e3181dbece1
Burnett, R., Chen, H., Szyszkowicz, M., Fann, N., Hubbell, B., Pope, C. A., III, … Cohen, A. (2018). Global estimates of mortality associated with long-term exposure to outdoor fine particulate matter. Proceedings of the National Academy of Sciences, 115(38), 9592–9597. https://doi.org/10.1073/pnas.1803222115
Chatfield, C. (2004). The analysis of time series: An introduction (6th ed.). Chapman & Hall/CRC.
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. https://doi.org/10.1145/2939672.2939785
Chicco, D., Warrens, M. J., & Jurman, G. (2021). The coefficient of determination R² is more informative than SMAPE, MAE, MAPE, MSE, and RMSE in regression analysis evaluation. PeerJ Computer Science, 7, e623. https://doi.org/10.7717/peerj-cs.623
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
Han, J., Kamber, M., & Pei, J. (2012). Data mining: Concepts and techniques (3rd ed.). Morgan Kaufmann.
Handhayani, T. (2023). Pemodelan prediksi kualitas udara berbasis deep learning pada data time-series multivariat [Disertasi/tesis tidak dipublikasikan]. Universitas Indonesia.
Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction (2nd ed.). Springer. https://doi.org/10.1007/978-0-387-84858-7
KLHK. (2020). Indeks standar pencemar udara (ISPU) Indonesia. Kementerian Lingkungan Hidup dan Kehutanan Republik Indonesia.
Little, R. J. A., & Rubin, D. B. (2019). Statistical analysis with missing data (3rd ed.). Wiley.
Liu, Y., Zhang, Q., & Wang, X. (2024). Multivariate time-series forecasting of PM2.5 using hybrid deep learning models. Environmental Modelling & Software, 170, 105760. https://doi.org/10.1016/j.envsoft.2023.105760
Lütkepohl, H. (2005). New introduction to multiple time series analysis. Springer. https://doi.org/10.1007/978-3-540-27752-1
Naz, S., Hussain, I., & Zafar, A. (2023). Machine learning-based air quality prediction: A comparative analysis. Sustainable Cities and Society, 91, 104430. https://doi.org/10.1016/j.scs.2023.104430
Oukhouya, L., El Hachimi, M., & Rhanoui, M. (2024). Deep learning models for air quality forecasting: A comparative study. Atmospheric Pollution Research, 15(2), 101995. https://doi.org/10.1016/j.apr.2024.101995
Pope, C. A., III, & 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. https://doi.org/10.1080/10473289.2006.10464485
Rubin, D. B. (1987). Multiple imputation for nonresponse in surveys. Wiley.
Rybarczyk, Y., & Zalakeviciute, R. (2020). Machine learning approaches for outdoor air quality modelling: A systematic review. Applied Sciences, 10(21), 7360. https://doi.org/10.3390/app10217360
Seinfeld, J. H., & Pandis, S. N. (2016). Atmospheric chemistry and physics: From air pollution to climate change (3rd ed.). Wiley.
van Buuren, S. (2018). Flexible imputation of missing data (2nd ed.). Chapman & Hall/CRC.
van Buuren, S., & Oudshoorn, C. G. M. (1999). Flexible multivariate imputation by MICE. TNO Prevention and Health.
World Bank Group. (2022). World development report 2022: Finance for an equitable recovery. World Bank. https://doi.org/10.1596/978-1-4648-1730-4
World Health Organization. (2021). WHO global air quality guidelines. WHO Press.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
