Prediction of Multivariate Air Quality Time Series Data using Long Short-Term Memory Network

Malaysia often suffers from haze problems almost every year. Therefore, there is a need for good air quality forecasting model monitoring and management purposes. In this study, the based on Long Short-Term Memory Network (LSTM) Auto-Regressive Integrated Moving Average (ARIMA) was developed. The prediction of particulate matter 10 micrometres or less in diameter (PM10) could be made both models, their performance compared. purpose comparison between two models to determine most suitable use predicting PM10 since it dominant pollutant time, especially during period. This study used data obtained Department Environment July 2017 June 2019. results showed that using multivariate LSTM better than univariate ARIMA with lowest root mean square error (RMSE) those selected stations. lower RMSE value means provide higher accuracy PM10.