Penerapan Vector Autoregressive Integrated Moving Average (VARIMA) Pada Prediksi Indeks Standar Pencemaran Udara

Abstract

Vector Autoregressive Integrated Moving Average (VARIMA) is a data forecasting approach multivariate time series which is used to determine the relationship between several variables at one time and variables in the previous period. One implementation of the VARIMA model is to predict the Air Pollution Standard Index (ISPU). The increasing number of factories and industrial activities is the main cause of air pollution in Gresik Regency. Therefore, this study aims to apply the model and predict ISPU concentrations using VARIMA. The data used in this research is daily data on concentrations of  PM_2.5, NO₂, and O₃  from November 2023 to February 2024. The results of this research show that the best model is based on the smallest RMSE and MAD values ?, the VARIMA model (2,1,1), where the concentrations PM_2.5 and O₃  at time t are influenced by the three variables at time (t-1), (t- 2), and (t-3) and is influenced by the residual values ??of the three variables at time (t-1). Meanwhile, the NO₂ variable at time t is only influenced by the PM_2.5 and O₃  variables at time (t-1), (t-2), and (t-3) and is influenced by the residual values ??of the three variables at time (t- 1).