Peramalan Pencemaran Udara Di Kota Surabaya Menggunakan Metode DSARIMA dengan Pendekatan Percentile Error Bootstrap (PEB)

Penulis

Novi Koesoemaningroem, Endroyono Endroyono, Supeno Mardi Susiki Nugroho

Abstrak

Peramalan pencemaran udara yang  akurat  diperlukan untuk mengurangi dampak pencemaran udara. Peramalan yang belum akurat akan berdampak kurang efektifnya tindakan yang dilakukan untuk mengantisipasi dampak pencemaran udara. Sehingga diperlukan sebuah pendekatan yang dapat mengetahui keakuratan plot data hasil peramalan. Penelitian ini dilakukan dengan tujuan melakukan peramalan pencemaran udara berdasarkan parameter PM10, NO2, CO, SO2, dan O3dengan metode DSARIMA. Data dalam penelitian ini sebanyak 8.760 data yang berasal dari Dinas Lingkungan Hidup Kota Surabaya. Berdasarkan hasil peramalan selama 168 jam kadar parameter PM10, NO2, SO2 dan O3 cenderung  menurun. Hasil peramalan selama 168 jam dengan menggunakan DSARIMA memberikan hasil peramalan yang nilainya mendekati data aktual terbukti dari polanya yang sesuai atau mirip dengan grafik plot data aktual dengan hasil ramalan. Dengan pendekatan PEB, selisih antara data aktual dan data ramalan kecil dan plot grafik PEB mengikuti plot grafik di data aktual, sehingga dapat dikatakan bahwa model sudah sesuai. Hasil akurasi terbaik yang dihasilkan adalah model DSARIMA dengan RMSE terkecil 0,59 didapatkan dari parameter CO yaitu ARIMA(0,1,[1,2,3])(0,1,1)24(0,1,1)168.

 

Abstract

Accurate air pollution forecasting is needed to reduce the impact of air pollution. Inaccurate forecasting will result in less effective actions taken to anticipate the impact of air pollution. So we need an approach that can determine the accuracy of the forecast data plot. This research was conducted with the aim of forecasting air pollution based on the PM10, NO2, CO, SO2, and O3 parameters using the DSARIMA method. The data in this study were 8.760 data from the Surabaya City Environmental Service. Based on the results of forecasting for 168 hours, the levels of PM10, NO2, SO2, and O3 parameters tend to decrease. Forecasting results for 168 hours using DSARIMA provide forecasting results whose values are close to the actual data as evidenced by the pattern that matches or is similar to the actual data plot graph with the forecast results. With the PEB approach, the difference between the actual data and the forecast data is small and the PEB graph plot follows the graph plot in the actual data, so it can be said that the model is appropriate. The best accuracy result is DSARIMA with the smallest RMSE 0,59 obtained from the CO parameter, namely ARIMA(0,1,[1,2,3])(0,1,1)24(0,1,1)168.

 

 

Teks Lengkap:

PDF

Referensi


ABHILASH, M. S. K., THAKUR, A., GUPTA, D., & SREEVIDYA, B. (2018). Time Series Analysis of Air Pollution in Bengaluru Using ARIMA Model. Advances in Intelligent Systems and Computing, Vol. 696, Pp. 413-426, 413–426.

CHRISDAYANTI, B., & SUHARSONO, A. (2015). Peramalan Kandungan Particulate Matter (PM10) dalam Udara Ambien Kota Surabaya Menggunakan Double Seasonal ARIMA (DSARIMA). Jurnal Sains Dan Seni ITS, 4(2).

DEEPTHI, L. R., AMRUTA, C. G., KRISHNAN, D., KUMAR, R. S., & SOURAV, S. (2020). A Novel Approach for Prediction of Air Pollutant Concentration. Proceedings of the 4th International Conference on Trends in Electronics and Informatics, ICOEI 2020, Icoei, 217–223. https://doi.org/10.1109/ICOEI48184.2020.9142907.

DUA, R. D., MADAAN, D. M., MUKHERJEE, P. M., & LALL, B. L. (2019). Real time attention based bidirectional long short-term memory networks for air pollution forecasting. Proceedings - 5th IEEE International Conference on Big Data Service and Applications, BigDataService 2019, Workshop on Big Data in Water Resources, Environment, and Hydraulic Engineering and Workshop on Medical, Healthcare, Using Big Data Technologies, 151–158. https://doi.org/10.1109/BigDataService.2019.00027.

FAISHOL, M. A., ENDROYONO, & IRFANSYAH, A. (2020). Prediksi Polusi Udara Perkotaan di Surabaya Menggunakan Recurrent Neural Network-Long Short Term Memory. Jurnal Ilmiah Teknologi Informasi (JUTI), 18(2), 102–114.

HAIZUM, N., RAHMAN, A., LEE, M. H., & TALIB, M. (2019). Hybrid Seasonal ARIMA and Artificial Neural Network in Forecasting Southeast Asia City Air Pollutant Index. 215–226.

HAMAMI, F., & DAHLAN, I. A. (2020). Univariate Time Series Data Forecasting of Air Pollution using LSTM Neural Network. 1–5.

https://doi.org/10.1109/icadeis49811.2020.9277393.

MADAAN, D., DUA, R., MUKHERJEE, P., & LALL, B. (2019). Vayuanukulani: Adaptive memory networks for air pollution forecasting. ArXiv:1904.03977, 1–5.

MAHAJAN, S., CHEN, L., & TSAI, T. (2017). An Empirical Study of PM2 . 5 Forecasting Using Neural Network. 2–8.

NABILLAH, I., & RANGGADARA, I. (2020). Mean Absolute Percentage Error untuk Evaluasi Hasil Prediksi Komoditas Laut. Journal of Information System, 5(2), 250–255.

https://doi.org/10.33633/joins.v5i2.3900.

PERATURAN PEMERINTAH REPUBLIK INDONESIA. (1999). Peraturan Pemerintah Indonesia Nomor 41 Tahun 1999 Tentang Pengendalian Pencemaran Udara.

TOMAR, N., PATEL, D., & JAIN, A. (2020). Air Quality Index Forecasting using Auto-regression Models. 2020 IEEE International Students’ Conference on Electrical, Electronics and Computer Science, SCEECS 2020. https://doi.org/10.1109/SCEECS48394.2020.216.

TSAI, Y. (2018). Air pollution forecasting using RNN with LSTM. 2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress(DASC/PiCom/DataCom/CyberSciTech), 1074–1079. https://doi.org/10.1109/DASC/PiCom/DataCom/CyberSciTec.2018.00178.

WAHYU, P. (2018). Pemenuhan Baku Mutu Udara Emisi dan Penangannya; Tinjauan atas Polutan Partikulat, NOx, SO2. Prosiding Seminar Nasional Dan Konsultasi Teknologi Lingkungan, 5(September), 32–41.

ZHU, H., & HU, J. (2019). Air quality forecasting using SVR with quasi-linear kernel. CITS 2019 - Proceeding of the 2019 International Conference on Computer, Information and Telecommunication Systems, 5–9. https://doi.org/10.1109/CITS.2019.8862114.




DOI: http://dx.doi.org/10.25126/jtiik.2021855216