The assessment of the relationship between fine particulate matter and related meteorological conditions

Name: Panida Soontornsalathun

Organization : Kasetsart University. The Center of Excellence on Petrochemical and Materials Technology

Name: Kornvipa Sirisawat

Organization : Kasetsart University. The Center of Excellence on Petrochemical and Materials Technology

Name: Natsuda Klinklan

Organization : Kasetsart University. The Center of Excellence on Petrochemical and Materials Technology

Name: Szymanski, Wladyslaw

Organization : Kasetsart University. The Center of Excellence on Petrochemical and Materials Technology

Name: Viganda Varabuntoonvit

Organization : Kasetsart University. The Center of Excellence on Petrochemical and Materials Technology

Email : fengvgv@ku.th

LCSH: Air Pollution

LCSH: Particulate matter -- Environmental aspects

LCSH: Meteorology

LCSH: Atmospheric chemistry

LCSH: Environmental monitoring

Abstract: The issue of PM2.5 in Thailand stands as a pressing national concern, demanding urgent solutions. Particularly in the Bangkok metropolitan region, PM2.5 values consistently surpass established standards, directly impacting the daily lives of residents. These levels tend to escalate during the winter season, spanning from October to March each year. Meteorological factors significantly influence the occurrence and accumulation of PM2.5; therefore, this research aims to investigate the correlation between these factors and PM2.5 levels in Bangkok. This research explores the correlation between meteorological factors and PM2.5 levels specifically in the Bangkok area. The Deep Neural Network (DNN) model was developed to predict PM2.5 concentration using meteorological factors. Additionally, the study tests the accuracy of the model predictions by using the Cascade Virtual Impactor (CAVI) to measure PM2.5 and compare it with the model predictions. The results demonstrate the predictive efficiency of the DNN model for PM2.5, showcasing an R-squared (R2) value of 0.6637 and a Root Mean Squared Error (RMSE) value of 12.8610. The value predicted from the DNN model when compared to the results from the Environment Agency and BKK measurements within the same area, exhibits a 59.06% discrepancy. Additionally, the values obtained from the measurement of CAVI show a difference of 35.33% when compared to the predicted average value. The results indicate that the predicted values still exhibit low accuracy. Therefore, further efforts should concentrate on refining the model and structuring the dataset systematically for data training purposes. Experimentation with adjusting the model to accommodate time series data, such as using an LSTM model, should also be considered.

King Mongkut's University of Technology North Bangkok. Central Library

Address: BANGKOK

Email: library@kmutnb.ac.th

Created: 2024

Modified: 2025-03-07

Issued: 2025-03-07

บทความ/Article

application/pdf

BibliograpyCitation : In Thai Institute of Chemical Engineering and Applied Chemistry. The 33st Thai Institute of Chemical Engineering and Applied Chemistry International Conference (TIChE 2024) (pp.304-311). Bangkok : Thai Institute of Chemical Engineering And Applied Chemistry

eng

©copyrights King Mongkut's University of Technology North Bangkok

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	TiChE 2024pp.304-311.pdf	791.44 KB	1	2025-09-08 11:58:58

ใช้เวลา

0.038455 วินาที