Pengujian Algoritma Long Short Term Memory untuk Prediksi Kualitas Udara dan Suhu Kota Bandung
DOI:
https://doi.org/10.61769/telematika.v15i1.340Keywords:
LSTM, prediksi, kualitas udara, PM10, ISPUAbstract
This study develops the LSTM modeling to predict time series data of air quality in the city of Bandung from the parameters PM10, ISPU, temperature, and humidity. Modeling LSTM with 4 hidden layers, the number of batch sizes that is 32, the optimizer is adam, value of epoch is 1000, and the loss function using Mean Squared Error. The LSTM modeling results show that the network has a fairly good performance in predicting training and testing. The modeling produces a fairly good prediction accuracy for 3 parameters (temperature, humidity, ISPU). This is indicated by the predicted RMSE value which is smaller than the standard deviation value of the dataset test. However, the prediction results generated from the four test parameters based on the order of the best are the prediction of humidity, temperature, ISPU, and PM10 with unfavorable predictive results.
Penelitian ini mengembangkan pemodelan LSTM untuk memprediksi data time series, yaitu kualitas udara di kota Bandung, dari parameter PM10, ISPU, suhu, dan kelembaban. Pemodelan LSTM dengan 4 hidden layer, penentuan jumlah batch size yaitu 32, penentuan optimizer adalah adam, epoch senilai 1000, dan penentuan fungsi loss menggunakan mean squared error. Hasil pemodelan LSTM menunjukkan bahwa jaringan memiliki kinerja yang cukup baik pada prediksi training dan testing. Pemodelan menghasilkan keakuratan prediksi yang cukup baik untuk 3 parameter (suhu, kelembaban, ISPU).Hal ini ditunjukkan dengan nilai RMSE prediksi yang lebih kecil dari nilai standar deviasi uji dataset. Namun, hasil prediksi yang dihasilkan dari keempat parameter pengujian berdasarkan urutan dari yang paling baik yaitu prediksi kelembaban, suhu, ISPU, dan PM10 dengan hasil prediksi yang kurang baik.
References
A. Hermawan. “SPKU: Sistem Prediksi Kualitas Udara (Studi Kasus: DKI Jakarta),” Skripsi. University of Technology Yogyakarta, Indonesia, 2019.
Robotorial. (Agustus 2019). “Kualitas udara terbaik dan terburuk di Indonesia (Rabu, 21/08/2019)”. [Daring]. Tersedia: https://beritagar.id/artikel/berita/kualitas-udara-terbaik-dan-terburuk-di-indonesia-rabu-1082019 [21 Jun 2020].
M. Y. Fathoni, “Implementasi Metode Fuzzy Time Series Cheng untuk prediksi konsentrasi gas NO2 di udara,” J. Sist. Inf. Bisnis, vol. 7, no. 1, hlm. 17, Mei 2017.
B. Warsito, A. Rusgiyono, dan M. A. Amirillah., “Pemodelan general regression neural network untuk prediksi tingkat pencemaran udara kota Semarang.,” Media Stat., vol. 1, no. 1, pp. 43–51, 2008.
Y. Aprianto, N. Nurhasanah, dan I. Sanubary, “Prediksi kadar particulate matter (PM10) untuk pemantauan kualitas udara menggunakan jaringan syaraf tiruan (studi kasus kota Pontianak),” J. Positron, vol. 8, no. 1, 2018.
B. Özbay, G. A. Keskin, Ş. Ç. Doğruparmak, dan S. Ayberk, “Predicting tropospheric ozone concentrations in different temporal scales by using multilayer perceptron models,” Ecol. Inform., vol. 6, no. 3-4, hlm. 242–247, Juli 2011.
S. Bahri, Syamsuddin, dan M. Hadijati, “Model wavelet neural network untuk pemodelan polusi udara di kota Mataram, Lombok, Nusa Tenggara Barat, Indonesia,” dalan Prosiding Seminar Nasional Matematika, Statistika, dan Aplikasinya, 2019, hlm. 43–56.
X. Song, dkk., “Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model,” J. Pet. Sci. Eng., vol. 186, hlm. 106682, Maet. 2020.
X. Song, J. Huang, dan D. Song, “Air quality prediction based on LSTM-Kalman model,” dalam 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), 2019, hlm. 695–699.
Z. Zhao, W. Chen, X. Wu, P. C. Y. Chen, dan J. Liu, “LSTM network: a deep learning approach for short-term traffic forecast,” IET Intell. Transp. Syst., vol. 11, no. 2, hlm. 68–75, Maret 2017.
“Keputusan Kepala Badan Pengendalian Dampak Lingkungan Nomor: Kep-107/Kabapedal/11/1997 tentang Pedoman Teknis Perhitungan Dan Pelaporan Serta Informasi Indeks Standar Pencemar Udara.”
H.-L. Yu, Y.-C. Lin, dan Y.-M. Kuo, “A time series analysis of multiple ambient pollutants to investigate the underlying air pollution dynamics and interactions,” Chemosphere, vol. 134, hlm. 571–580, Sept 2015.
A. Kurniawan, “Pengukuran parameter kualitas udara (CO, NO2, SO2, O3 dan PM10) di Bukit Kototabang berbasis ISPU,” J. Teknosains, vol. 7, no. 1, 2017.
A. Yadav, C. K. Jha, dan A. Sharan, “Optimizing LSTM for time series prediction in Indian stock market,” Procedia Comput. Sci., vol. 167, hlm. 2091–2100, 2020.
Downloads
Published
Issue
Section
License
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation.
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.