Comparison of Methods for Analysis of the Air Quality: A Case Study of Alternative Energy for Biogas in Suphanburi Province

Abstract

This research examines the comparison of 96 monthly air quality data from biogas alternative energy in Suphan-Buri province for a total of 8 years from January 2010 to December 2017. By dividing the biogas composition data for analysis to the research objectives by dividing the data into two sets; namely the first set of data to create a model for forecasting trends in air quality to find suitability and the second set of information to compare the performance of air quality forecasting. The air quality forecasting using four time-series data forecasting methods; namely the Box-Jenkins Method (BJ), the Holt's Exponential Smoothing Method (Holt), the smoothing method with Brown's Exponential Smoothing Method (Brown) and the Damped trend exponential smoothing method (Damped). The composition of biogas is separated into 3 types of gases, namely methane (CH₄), carbon dioxide (CO₂) and hydrogen sulfide (H₂S) to determine the suitability of the forecast model. The results of the forecast model study by comparing the root mean square errors (RMSE) showed that the Damped method was suitable for CH₄ gas, the BJ method was suitable for CO₂ gas, and the Holt method was suitable for H₂S gas, respectively. The resulting model was then used to find future forecast values. It was found that the Damped method was able to generate a CH₄ gas data forecast model that was closest to the true value.