10.14456/ea.2024.16
Accurate Model for Forecasting PM2.5 Concentrations in Hat Yai, Songkhla, Thailand: The ARIMA-ANN-REG HybridApproach via AAR4PM
รหัสดีโอไอ
10.14456/ea.2024.16
Creator 1. Sasira Choojam
2. Jularat Chumnaul
3. Korakot Wichitsa-nguan Jetwanna
Title Accurate Model for Forecasting PM2.5 Concentrations in Hat Yai, Songkhla, Thailand: The ARIMA-ANN-REG HybridApproach via AAR4PM
Publisher Thai Society of Higher Education Institutes on Environment
Publication Year 2567
Journal Title EnvironmentAsia
Journal Vol. 17
Journal No. 2
Page no. 1-15
Keyword Time series, Auto-regressive integrated moving average, Artificial neural network, Hybrid model, Forecasting
URL Website http://www.tshe.org/ea/index.html
Website title EnvironmentAsia
ISSN 1906-1714
Abstract PM2.5 is a significant factor in the troubling air quality that presently affects many countries globally. Therefore, dependable prediction models are needed for the government to enable preparedness for severe PM2.5 situations. This study introduces the ARIMA-ANN-REG model to forecast PM2.5 concentrations in Hat Yai, Songkhla, Thailand. The efficiency of the proposed model was assessed against the auto-regressive integrated moving average (ARIMA), artificial neural network (ANN), and ARIMA-ANN models. Data used in this study was gathered from the Hat Yai Air Quality Monitoring Station spanning January 1st, 2016, to June 30th, 2022. To develop the model, 70% of the data retrieved between January 1st, 2016, and November 7th, 2020, was utilized for model training, while the remaining 30% was reserved for model testing. In determining the precision of the proposed model, evaluation criteria such as the root mean squared error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) were employed. The findings showcased the ARIMA-ANN-REG model's superior performance, exhibiting the lowest relative errors among the compared models. In addition, AAR4PM web application was developed for users who want to automatically build the ARIMA, ANN, ARIMA-ANN, and ARIMA-ANN-REG models with their own series data. It can be freely accessed at https://jularatchumnaul.shinyapps.io/AARt4PM/.
สมาคมอุดมศึกษาสิ่งแวดล้อมไทย

บรรณานุกรม

EndNote

APA

Chicago

MLA

ดิจิตอลไฟล์

Digital File
DOI Smart-Search
สวัสดีค่ะ ยินดีให้บริการสอบถาม และสืบค้นข้อมูลตัวระบุวัตถุดิจิทัล (ดีโอไอ) สำนักการวิจัยแห่งชาติ (วช.) ค่ะ