PERBANDINGAN PREDIKSI POLUSI UDARA MENGGUNAKAN LSTM DAN BILSTM
DOI:
https://doi.org/10.54314/jssr.v8i3.3596Abstrak
Abstract: Air pollution has become a serious problem in densely populated urban areas such as DKI Jakarta. To mitigate its negative impacts, an accurate air pollution prediction system is necessary. This study compares the performance of two deep learning models, Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (BiLSTM), in predicting PM10 concentration using air quality data from DKI Jakarta between 2016 and 2019. The research process includes data collection and preprocessing, model training, and model evaluation. Both models were tested with various parameters such as the number of hidden neurons, dropout rate, epochs, and batch size. The results consistently show that BiLSTM outperforms LSTM, achieving lower Root Mean Square Error (RMSE) values across 54 testing scenarios. The best BiLSTM configuration, with 64 hidden neurons, 0.2 dropout rate, 50 epochs, and batch size 16, yielded an RMSE of 9.311401. Meanwhile, the best LSTM configuration, with 128 hidden neurons, 0.1 dropout rate, 100 epochs, and batch size 16, produced an RMSE of 9.330554. The advantage of BiLSTM lies in its ability to process data bidirectionally, making it more effective in capturing temporal patterns for air pollution prediction compared to LSTM.
Â
Keywords: air pollution prediction, pollutant, deep learning, LSTM, BiLSTM
Â
Abstrak: Pencemaran udara menjadi masalah serius di wilayah perkotaan padat seperti DKI Jakarta. Untuk mengurangi dampak negatifnya, diperlukan sistem prediksi polusi udara yang akurat. Penelitian ini membandingkan performa dua model deep learning, Long Short-Term Memory (LSTM) dan Bidirectional Long Short-Term Memory (BiLSTM), dalam memprediksi konsentrasi PM10 menggunakan data kualitas udara DKI Jakarta tahun 2016-2019. Proses penelitian mencakup pengumpulan dan praproses data, pelatihan model, serta evaluasi model. Kedua model diuji dengan berbagai parameter seperti jumlah hidden neuron, dropout rate, epoch, dan batch size. Hasil menunjukkan BiLSTM lebih unggul secara konsisten dengan nilai Root Mean Square Error (RMSE) lebih rendah melalui 54 skenario pengujian. Konfigurasi terbaik BiLSTM menggunakan 64 hidden neuron, dropout rate 0.2, 50 epoch, dan batch size 16 menghasilkan RMSE 9.311401. Sedangkan konfigurasi LSTM terbaik pada 128 hidden neuron, dropout rate 0.1, 100 epoch, dan batch size 16 menghasilkan RMSE 9.330554. Keunggulan BiLSTM terletak pada kemampuannya memproses data dua arah, sehingga lebih efektif dalam menangkap pola temporal untuk prediksi polusi udara dibandingkan LSTM.Â
Â
Kata kunci: prediksi polusi udara, polutan, deep learning, LSTM, BiLSTM
Unduhan
Referensi
Akanksha, A., Maurya, N., Jain, M., & Arya, S. (2023). Prediction And Analysis of Air Pollution Using Machine Learning Algorithms. 2023 3rd International Conference on Intelligent Technologies (CONIT), 1–6. https://doi.org/10.1109/CONIT59222.2023.10205615
Almetwally, A. A., Bin-Jumah, M., & Allam, A. A. (2020). Ambient air pollution and its influence on human health and welfare: an overview. Environmental Science and Pollution Research International, 27(20), 24815–24830. https://doi.org/10.1007/s11356-020-09042-2
Amalia, A. P., Zaidiah, A., & Isnainiyah, I. N. (2022). Prediksi Kualitas Udara Menggunakan Algoritma K-Nearest Neighbor. JIPI (Jurnal Ilmiah Penelitian Dan Pembelajaran Informatika). https://api.semanticscholar.org/CorpusID:251416679
Chen, K., Purba, R., & Halim, A. (2022). Stock Price Prediction Using XCEEMDAN-Bidirectional LSTM -Spline. Indonesian Journal of Artificial Intelligence and Data Mining, 5(1), 1. https://doi.org/10.24014/ijaidm.v5i1.14424
DESA, U. N. (2018). 2018 Revision of World Urbanization Prospects. United Nations News. https://www.un.org/zh/desa/2018-revision-world-urbanization-prospects
Dhake, H., Kashyap, Y., & Kosmopoulos, P. (2023). Algorithms for Hyperparameter Tuning of LSTMs for Time Series Forecasting. Remote Sensing, 15(8). https://doi.org/10.3390/rs15082076
Hua, Y. (2020). Bitcoin price prediction using ARIMA and LSTM. E3S Web of Conferences. https://api.semanticscholar.org/CorpusID:234616966
Lestari, I., & Mahendra, I. (2023). Prediksi Kualitas Udara dengan Menggunakan Metode Long Short-Term Memory dan Artificial Neural Network. Jurnal Sistem Dan Informatika (JSI), 17, 121–129. https://doi.org/10.30864/jsi.v17i2.565
Lu, J., Li, B., Li, H., & Al-Barakani, A. (2021). Expansion of city scale, traffic modes, traffic congestion, and air pollution. Cities, 108, 102974. https://doi.org/https://doi.org/10.1016/j.cities.2020.102974
Mitreska Jovanovska, E., Batz, V., Lameski, P., Zdravevski, E., Herzog, M. A., & Trajkovik, V. (2023). Methods for Urban Air Pollution Measurement and Forecasting: Challenges, Opportunities, and Solutions. Atmosphere, 14(9). https://doi.org/10.3390/atmos14091441
Peng, T., Zhang, C., Zhou, J., & Nazir, M. S. (2021). An integrated framework of Bi-directional long-short term memory (BiLSTM) based on sine cosine algorithm for hourly solar radiation forecasting. Energy, 221, 119887. https://doi.org/https://doi.org/10.1016/j.energy.2021.119887
Pratama, A. (2024). Bitcoin Cryptocurrency Price Prediction Using IFA-BiLSTM. 2024 2nd International Conference on Technology Innovation and Its Applications (ICTIIA), 1–6. https://doi.org/10.1109/ICTIIA61827.2024.10761776
Raheja, S., & Malik, S. (2022). Prediction of Air Quality Using LSTM Recurrent Neural Network. International Journal of Software Innovation, 10, 1–16. https://doi.org/10.4018/IJSI.297982
Rahman, M. M., Nayeem, M. E. H., Ahmed, M. S., Tanha, K. A., Sakib, M. S. A., Uddin, K. M. M., & Babu, H. M. H. (2024). AirNet: predictive machine learning model for air quality forecasting using web interface. Environmental Systems Research, 13(1), 44. https://doi.org/10.1186/s40068-024-00378-z
Ravindiran, G., Hayder, G., Kanagarathinam, K., Alagumalai, A., & Sonne, C. (2023). Air quality prediction by machine learning models: A predictive study on the indian coastal city of Visakhapatnam. Chemosphere, 338, 139518. https://doi.org/https://doi.org/10.1016/j.chemosphere.2023.139518
Seabe, P. L., Moutsinga, C. R. B., & Pindza, E. (2023). Forecasting Cryptocurrency Prices Using LSTM, GRU, and Bi-Directional LSTM: A Deep Learning Approach. Fractal and Fractional, 7(2). https://doi.org/10.3390/fractalfract7020203
