Open AccessA Generalized Space-Time Autoregressive Moving Average (GSTARMA) Model for Forecasting Air Pollutant in Surabaya
Author(s) -
Muhammad Sjahid Akbar,
Setiawan Setiawan,
Suhartono Suhartono,
Budi Nurani Ruchjana,
Dedy Dwi Prastyo,
Amri Muhaimin,
Endah Setyowati
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1490/1/012022
Subject(s) - autoregressive model , statistics , autoregressive integrated moving average , mathematics , series (stratigraphy) , autoregressive–moving average model , ordinary least squares , residual , time series , multivariate statistics , mean squared error , econometrics , algorithm , paleontology , biology
The GSTAR model is a multivariate time series model that has time and location dependencies. The implementation of the GSTAR model was developed using the GSTARMA model by referring to the Autoregressive Moving Average (ARMA) model. This research provides the early warning stage of air pollution in Surabaya by forecasting the content of pollutant, especially the CO (Carbon monoxide). The data used in this research are CO data are taken from three monitoring stations in Surabaya with a period from January, 1 st to December 31 st , 2018. There are two stages in this research, the first stage is time series regression with a dummy variable from the data pattern, and the second step is modeling residual time series regression with GSTAR and GSTARMA. This research is using two weights, uniform and inverse weight the distances, with two-parameter estimates, namely OLS and SUR. The results given the RMSE values tend to be small by using GSTARMAX(2 1 ,[7] 1 :) model with an inverse weight the distance and OLS parameter estimation for SUF 1, GSTAR(2 1 ) model with an inverse weight the distance using SUR parameter estimation on SUF 6, and GSTARMA(2 1 ,[7] 1 ) model using an inverse weight the distance and SUR parameter estimation on SUF 7. Based on the results of this research, the GSTARMA model can correct prediction errors from the GSTAR model on CO data.