Pemodelan Pencemaran Udara sebagai Solusi Penurunan Kualitas Udara Menggunakan Generalized Space-Time Autoregressive di Kota Makassar

This study discusses the application of the Generalized Space-Time Autoregressive (GSTAR) model to analyze air pollution in Makassar City, focusing on NO2 and SO2 pollutants from 2017 to 2023. Data were collected from four different sampling locations: transportation, industry, residential, and office areas. This study uses inverse distance weighting and cross-correlation normalization to develop the forecasting model. The analysis results show that the GSTAR (1;0;2) model for NO2 pollutants and GSTAR (1;0;1) for SO2 pollutants are the best models, with residuals meeting the assumptions of white noise and normal distribution. Therefore, this model can be used to predict future air pollution levels.