PREDIKSI RATA-RATA ZAT BERBAHAYA DI DKI JAKARTA BERDASARKAN INDEKS STANDAR PENCEMAR UDARA MENGGUNAKAN METODE LONG SHORT-TERM MEMORY
Manajemen Sistem Informasi, Program Pasca Sarjana, Universitas Gunadarma
Indonesia
Manajemen Sistem Informasi, Program Pasca Sarjana, Universitas Gunadarma
Indonesia
Abstract
Indonesia menempati peringkat ke-6 dari 98 negara paling berpolusi di dunia pada tahun 2019. Di tahun tersebut, rata-rata AQI (Air Quality Index) sebesar 141 dan rata-rata konsentrasi PM2.5 sebesar 51.71 μg/m3 yang lima kali lipat diatas rekomendasi World Health Organization (WHO). Salah satu kota penyumbang polusi udara yaitu Jakarta. Berdasarkan data ISPU (Indeks Standar Pencemar Udara) yang diambil dari SPKU (Stasiun Pemantau Kualitas Udara) Dinas Lingkungan Hidup DKI Jakarta melampirkan pada tahun 2019, Jakarta memiliki kualitas udara sangat tidak sehat. Oleh karena itu perlu adanya model Artificial Intelligence dalam memperdiksi rata-rata tingkat zat berbahaya pada udara di DKI Jakarta. Salah satu algoritma yang dapat diterapkan dalam membuat model prediksi dengan menggunakan data timeseries adalah Long Short-Term Memory (LSTM). Tujuan dari penelitian ini membangun model prediksi rata-rata ISPU di DKI Jakarta menggunakan metode LSTM yang berguna bagi para pemangku kepentingan dibidang lingkungan hidup khususnya mengenai polusi udara. Penelitian mengenai prediksi rata-rata ISPU di DKI Jakarta menggunakan metode LSTM, menghasilkan nilai evaluasi MAPE 12.28%. Berdasarkan hasil evaluasi MAPE yang diperoleh, model LSTM yang digunakan untuk prediksi rata-rata ISPU di DKI Jakarta masuk kedalam kategori akurat.
Keywords
References
A. Ahmad, “Mengenal Artificial Intelligence, Machine Learning, Neural Network, dan Deep Learning,” in Academia, 2017. [Online] Available: https://www.academia.edu [Accessed: Nov 26, 2020].
IQAir, “World Air Quality,” 2019 World Air Qual. Rep., pp. 1–22, 2019, [Online]. Available: https://www.iqair.com/world-most-polluted-cities/world-air-quality-report-2019-en.pdf. [Accessed: Nov 26, 2020].
AQIAir, “AQIAir Website.” [Online] Available: https://www.iqair.com. [Accessed: Nov 26, 2020].
L. Arumingtyas, “Jakarta Air Quality,” mongabay.com, para. 8, Apr. 25, 2020. [Online] https://www.mongabay.co.id/2020/04/25/polusi-udara-pembunuh-senyap-di-jabodetabek/. [Accessed: Nov 26, 2020].
C. T. Yang, L. Y. Lin, Y. T. Tsan, P. Y. Liu, and W. C. Chan, “The Implementation of a Real-time Monitoring and Prediction System of PM2.5 and Influenza-Like Illness Using Deep Learning,” J. Internet Technol., vol. 20, no. 7, pp. 2237–2245, 2019, doi: 10.3966/160792642019122007020. [Online Serial]. Available: https://jit.ndhu.edu.tw/article/view/2210. [Accessed: Dec. 1, 2020]
V. Chaudhary, A. Deshbhratar, V. Kumar, and D. Paul, “Time Series Based LSTM Model to Predict Air Pollutant ’ s Concentration for Prominent Cities in India,” Udm’18, 2018. [Online Serial]. Available: http://philippe-fournier-viger.com/utility_mining_workshop_2018/PAPER1.pdf. [Accessed: Dec. 1, 2020].
Y. Sudriani, I. Ridwansyah, and H. A Rustini, “Long short term memory (LSTM) recurrent neural network (RNN) for discharge level prediction and forecast in Cimandiri river, Indonesia,” IOP Conf. Ser. Earth Environ. Sci., vol. 299, no. 1, 2019, doi: 10.1088/1755-1315/299/1/012037. [Online Serial]. Available: https://iopscience.iop.org/article/10.1088/1755-1315/299/1/012037. [Accessed Dec. 5, 2020].
T. Li, M. Hua, and X. U. Wu, “A Hybrid CNN-LSTM Model for Forecasting,”IEEE Access, vol. 8, Feb, 2020. [Online serial]. Available: https://ieeexplore.ieee.org/abstract/document/8979420. [Accessed Dec. 2, 2020].
V. Reddy, P. Yedavalli, S. Mohanty, and U. Nakhat, “Deep Air: Forecasting Air Pollution in Beijing, China,” 2017. [Online Serial] Available: https://www.semanticscholar.org/paper/Deep-Air-%3A-Forecasting-Air-Pollution-in-Beijing-%2C-Reddy-Mohanty/271279939e545be172f7b754b67d6811c11c8fae. [Accessed Dec. 7, 2020].
K. S. Rao, G. L. Devi, and N. Ramesh, “Air Quality Prediction in Visakhapatnam with LSTM based Recurrent Neural Networks,” Int. J. Intell. Syst. Appl., vol. 11, no. 2, pp. 18–24, 2019, doi: 10.5815/ijisa.2019.02.03. [Online Serial] Available: https://www.semanticscholar.org/paper/Air-Quality-Prediction-in-Visakhapatnam-with-LSTM-Rao-Devi/f34d77e3375bd512d14abe3cbacc29e31a2f83aa. [Accessed Dec. 7, 2020].
Y. A. Ayturan et al., “Short-term prediction of pm2.5 pollution with deep learning methods,” Glob. Nest J., vol. 22, no. 1, pp. 126–131, 2020, doi: 10.30955/gnj.003208. [Online Serial] Available: https://journal.gnest.org/publication/gnest_03208 [Accessed Dec. 10, 2020].
J. Lu, P. Bu, X. Xia, L. Yao, Z. Zhang, and Y. Tan, “A New Deep Learning Algorithm for Detecting the Lag Effect of Fine Particles on Hospital Emergency Visits for Respiratory Diseases,” IEEE Access, vol. 8, pp. 145593–145600, 2020, doi: 10.1109/ACCESS.2020.3013543. [Online Serial] Available: https://ieeexplore.ieee.org/document/9153761 [Accessed Dec. 10, 2020].
T. Xayasouk, H. M. Lee, and G. Lee, “Air pollution prediction using long short-term memory (LSTM) and deep autoencoder (DAE) models,” Sustain., vol. 12, no. 6, 2020, doi: 10.3390/su12062570. [Online Serial] Available: https://www.mdpi.com/2071-1050/12/6/2570 [Accessed Dec. 10, 2020].
Y. Zhu and X. Zhou, “Prediction of Air Quality Index Based on Wavelet Transform Combination Model,” Proc. - 2019 11th Int. Conf. Intell. Human-Machine Syst. Cybern. IHMSC 2019, vol. 1, no. Itaic, pp. 157–160, 2019, doi: 10.1109/IHMSC.2019.00044. [Online Serial] Available: https://ieeexplore.ieee.org/document/8941558 [Accessed Dec. 13, 2020].
J. J. Montaño Moreno, A. Palmer Pol, A. Sesé Abad, and B. Cajal Blasco, “El índice R-MAPE como medida resistente del ajuste en la previsiońn,” Psicothema, vol. 25, no. 4, pp. 500–506, 2013, doi: 10.7334/psicothema2013.23. [Online Serial] Available: https://dialnet.unirioja.es/servlet/articulo?codigo=4655890 [Accessed Dec. 13, 2020].
C.Lewis, Industrial and Business Forecasting Methods. London: Butterworth-Heinemann, 1982.
