Comparison of Multiple Linear Regression and Periodic Models for Estimating PM2.5 and PM10 Concentrations in Bangkok
DOI:
https://doi.org/10.59796/jcst.V15N3.2025.117Keywords:
Bangkok, multiple linear regression, periodic model, PM10, PM2.5Abstract
This study compares the performance of Multiple Linear Regression (MLR) and Periodic Models in estimating PM2.5 and PM10 concentrations in Bangkok using a 60-month dataset (2019–2023). Eight independent variables, including air temperature, rainfall, air pressure, wind speed, ozone concentrations, nitrogen dioxide concentrations, the number of vehicles, and the number of factories, were analyzed to determine their influence on PM2.5 and PM10 levels. Model accuracy was assessed using Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE). The results revealed that the Periodic Model more accurately predicted PM2.5 (MAE = 4.65, MAPE = 12.69), while the MLR model performed better for PM10 (MAE = 6.93, MAPE = 10.54). These findings highlight the complementary strengths of the two modeling approaches: Periodic Models effectively capture seasonal trends, while MLR reveals specific influencing factors. These findings provide valuable insights into the strengths and limitations of each model, offering guidance for developing targeted and efficient measures to control PM2.5 and PM10 levels in Bangkok, ultimately enhancing public health and urban living conditions.
References
An, A. (2025). An AIoT-based air quality monitoring system for real-time PM2.5 prediction in urban environments. ASEAN Journal of Scientific and Technological Reports, 28(1), Article e255168. https://doi.org/10.55164/ajstr.v28i1.255168
Annette, J. D. (1990). An introduction to generalized linear models (5th ed.). New South Wales, USA: Chapman & Hall.
Botchkarev, A. (2019). Performance metrics (error measures) in machine learning regression, forecasting and prognostics: Properties and typology. Interdisciplinary Journal of Information, Knowledge, and Management, 14, 45-76. https://doi.org/10.48550/arXiv.1809.03006
Climate Center, Thai Meteorological Department. (2024). Weather summary (monthly). Retrieved from https://www.tmd.go.th/en/climate/summarymonthly
Department of Industrial Works. (2024). Industrial factory statistics. Retrieved from https://www.diw.go.th/webdiw/static-fac/
Kanchanasuta, S., Ingviya, T., Dumavibhat, N., Wongrathanandha, C., Sansanayudh, N., Chalongviriyalert, P., ... & Bunplod, N. (2024). Constructing an AQHI as a health risk communication tool for Bangkok, Thailand. Environmental Challenges, 16, Article 100991. https://doi.org/10.1016/j.envc.2024.100991
Kanchanasuta, S., Sooktawee, S., Patpai, A., & Vatanasomboon, P. (2020). Temporal variations and potential source areas of fine particulate matter in Bangkok, Thailand. Air, Soil and Water Research, 13, Article 1178622120978203. https://doi.org/10.1177/1178622120978203
Laohakiat, S., Klerkkidakan, S., & Wiwatwattana, N. (2024). Visually estimating and forecasting PM2.5 levels using hybrid architecture deep neural network. Current Applied Science and Technology, 24(3), Article e0258074. https://doi.org/10.55003/cast.2023.258074
Lippman, D., & Rasmussen, M. (2022). Precalculus: An investigation of functions (2nd ed.). USA: Creative Commons.
Meteostat. (2024). Weather data. Retrieved from https://meteostat.net/en/station/48455?t=2019-01-01/2019-01-01
Minsan, W., Minsan, P., & Panichkitkosolkul, W. (2024). Enhancing decomposition and Holt-winters weekly forecasting of PM2.5 concentrations in Thailand’s eight northern provinces using the Cuckoo Search algorithm. Thailand Statistician, 22(4), 963–985. https://ph02.tci-thaijo.org/index.php/thaistat/article/view/256084
Pengjan, S., Fan, C., Bonnet, S., & Garivait, S. (2019). Assessment of the PM2.5/PM10 ratio in the Bangkok Metropolitan Region during. Journal of Sustainable Energy & Environment, 10, 75-84.
Pollution Control Department. (2024). Regional air quality and situation reports. Retrieved from http://air4thai.pcd.go.th/webV3/#/History
Pranonsatit, J., Wongwailikhit, K., Painmanakul, P., Vateekul, P. (2025). Enhancing PM2.5 forecasting using video-based spatiotemporal models and cyclical encoding. In Nguyen, N.T., et al. Recent Challenges in Intelligent Information and Database Systems. ACIIDS 2025. Communications in Computer and Information Science, 2494. Springer, Singapore. https://doi.org/10.1007/978-981-96-5884-8_26
Sirisumpun, N., Wongwailikhit, K., Painmanakul, P., & Vateekul, P. (2023). Spatio-Temporal PM2. 5 Forecasting in Thailand Using Encoder-Decoder Networks. IEEE Access, 11, 69601-69613. https://doi.org/10.1109/ACCESS.2023.3293398
Sooktawee, S., Kanchanasuta, S.,base & Bunplod, N. (2023). Assessment of 24-h moving average PM2. 5 concentrations in Bangkok, Thailand against WHO guidelines. Sustainable Environment Research, 33(1), Article 3. https://doi.org/10.1186/s42834-023-00165-y
Tesfaldet, Y. T., & Chanpiwat, P. (2023). The effects of meteorology and biomass burning on urban air quality: The case of Bangkok. Urban Climate, 49, Article 101441. https://doi.org/10.1016/j.uclim.2023.101441
Transport Statistics Group, Planning Division, Department of Land Transport. (2024). Number of new registered cars. Retrieved from https://web.dlt.go.th/statistics/
Wang, X., & Liu, Y. (2019). Research on the application of improved least square method in linear fitting. IOP Conference Series: Earth and Environmental Science, 252, 052158. https://doi.org/10.1088/1755-1315/252/5/052158
World Health Organization (WHO). (2021). WHO global air quality guidelines: Particulate matter (PM2.5 and PM10), ozone, nitrogen dioxide, sulfur dioxide, and carbon monoxide. Retrieved from https://apps.who.int/iris/handle/10665/345329
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2025 Journal of Current Science and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
