Spatio-Temporal Forecasting of Air Pollution in Jakarta Using Deep Learning Methods

Ahmad Saikhu*, Arsy Bilahil Tama, Muhammad Zulfikar Fauzi, Alfan Alfarisy

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publication2023 14th International Conference on Information and Communication Technology and System, ICTS 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages188-192
Number of pages5
ISBN (Electronic)9798350312164
DOIs
Publication statusPublished - 2023
Event14th International Conference on Information and Communication Technology and System, ICTS 2023 - Surabaya, Indonesia
Duration: 4 Oct 20235 Oct 2023

Publication series

Name2023 14th International Conference on Information and Communication Technology and System, ICTS 2023

Conference

Conference14th International Conference on Information and Communication Technology and System, ICTS 2023
Country/TerritoryIndonesia
CitySurabaya
Period4/10/235/10/23

Keywords

  • Air Pollution
  • Deep Learning
  • Forecasting
  • Spatiotemporal

Fingerprint

Dive into the research topics of 'Spatio-Temporal Forecasting of Air Pollution in Jakarta Using Deep Learning Methods'. Together they form a unique fingerprint.

Cite this