Advancing precision in air quality forecasting through machine learning integration

Abstrak

In an era where environmental concerns are escalating, air quality forecasting emerges. Forecasting is a crucial tool for addressing the adverse impacts of pollution on public health and ecosystems. In urban centers like Bandar Lampung, economic activities intensify pollution levels. This condition leveraging advanced machine learning forecasting methods can significantly mitigate these effects. This study evaluates the precision of long short-term memory (LSTM) and Prophet methods in predicting air quality. This study utilizes data from January 12, 2022 to November 9, 2023. The results reveal a distinct advantage of the LSTM method over the Prophet. The LSTM method showcases superior accuracy across all evaluation metrics. Specifically, the LSTM method achieved an average root mean squared error (RMSE) of 5.38, mean absolute error (MAE) of 3.94, and mean absolute percentage error (MAPE) of 0.07. In contrast, the Prophet method recorded higher error rates, with an average RMSE of 18.48, MAE of 15.61, and MAPE of 0.25. These numbers underscore the LSTM method's robustness and reliability in forecasting air quality. The result highlights its potential as a pivotal resource for environmental monitoring and policymaking to safeguard public health and promote sustainable urban development.