Comparison of Anomaly Detection Using Statistical Method and Deep Learning Method in Jakarta Air Quality Index Data

Anomaly in the air quality index (AQI) is essential to detect as an early warning of air pollution disasters that may occur in the future.Therefore, recognizing the characteristics of anomaly detection methods in AQI data is crucial.This research aims to compare the statistical and deep learning methods in detecting anomalies in the Jakarta AQI data.The data used is Jakarta AQI and calendar variation from January 1, 2019, to February 29, 2024.The method used in this study is a statistical method, namely distributed lag, and a deep learning method, namely autoencoder and LSTM autoencoder, where this method detects anomalies based on the four-sigma rule.The characteristics of anomaly detection using the distributed lag method tend to be more sensitive, with low false negative values and high false positive values.Meanwhile, anomaly detection using the autoencoder method tends to have a high false negative value with a low false positive value.On the other hand, anomaly detection using the LSTM autoencoder method tends to have a low false negative value with a false positive value that is not too high.Considering the characteristics of the methods, the distributed lag method is more recommended.