@inproceedings{c8bc86b08c43483b991084f8783bc61c,
title = "Spatio-Temporal Forecasting of Air Pollution in Jakarta Using Deep Learning Methods",
abstract = "Air pollution has always been a prominent problem that can cause severe health problems for humanity. Fine particulate matter are particles that contribute directly to this phenomenon, the higher the value the more pollution it indicates. The Jakarta air quality index at the time of this study is very high and determined to be unhealthy by the World Health organization standard. Forecasting of this value can help humans to act accordingly to minimize the adverse effects. In this study, an air pollution forecast utilizing spatio-temporal data is developed to address the problem. Multiple deep learning techniques such as Gated Recurrent Unit, Long-Short Term Memory, and bidirectional Long-Short Term Memory were used in this study. The results from this study showed that Long-Short Term Memory performs best in air pollution forecasting using spatio-temporal data achieving the lowest Mean Absolute Percentage Error value of 1.25% percent and highest R-Square value of 0.998.",
keywords = "Air Pollution, Deep Learning, Forecasting, Spatiotemporal",
author = "Ahmad Saikhu and Tama, {Arsy Bilahil} and Fauzi, {Muhammad Zulfikar} and Alfan Alfarisy",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 14th International Conference on Information and Communication Technology and System, ICTS 2023 ; Conference date: 04-10-2023 Through 05-10-2023",
year = "2023",
doi = "10.1109/ICTS58770.2023.10330856",
language = "English",
series = "2023 14th International Conference on Information and Communication Technology and System, ICTS 2023",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "188--192",
booktitle = "2023 14th International Conference on Information and Communication Technology and System, ICTS 2023",
address = "United States",
}