Forecasting PM2.5 Quantity in Nakhon Ratchasima Province Using Time Series and Machine Learning
Article Sidebar
Main Article Content
Abstract
This research aimed to create models to forecast monthly PM2.5 quantity in Nakhon Ratchasima province by using 3 methods including Box-Jenkins method, Multiple linear regression and Artificial neural networks and to compare the performance of the forecasting models using Root mean square error (RMSE). For creating forecasting models, the data set 1 of PM2.5 quantity collected from 42 time periods from July 2019 to December 2022 was used while for the performance comparison among the forecasting models, the data set 2 of PM2.5 quantity collected from 12 time periods from January 2023 to December 2023 was used. The results demonstrated that the Artificial neural network was the suitable model for forecasting monthly PM2.5 quantity in Nakhon Ratchasima province. This model consisted of 14 inputs, 1 hidden layer with 7 nodes, a learning rate of 0.1, a momentum of 0.1, and 500 epochs. Furthermore, it had the lowest RMSE of 2.560 and a coefficient of determination (R2) of 0.988.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
บทความที่ได้รับการตีพิมพ์เป็นลิขสิทธิ์ของ วารสารวิทยาศาสตร์และเทคโนโลยี มหาวิทยาลัยอุบลราชธานี
ข้อความที่ปรากฏในบทความแต่ละเรื่องในวารสารวิชาการเล่มนี้เป็นความคิดเห็นส่วนตัวของผู้เขียนแต่ละท่านไม่เกี่ยวข้องกับมหาวิทยาลัยอุบลราชธานี และคณาจารย์ท่านอื่นๆในมหาวิทยาลัยฯ แต่อย่างใด ความรับผิดชอบองค์ประกอบทั้งหมดของบทความแต่ละเรื่องเป็นของผู้เขียนแต่ละท่าน หากมีความผิดพลาดใดๆ ผู้เขียนแต่ละท่านจะรับผิดชอบบทความของตนเองแต่ผู้เดียว
References
Pochanart, P. 2016. The present state of urban air pollution problems in Thailand’s large cities: cases of Bangkok, Chiang mai, and Rayong. Journal of Environmental Management. 12(1):114-33. (in Thai)
Department of Disease Control. 2023. Disease and Health Hazard Forecast for Week No. 9/2022. https://ddc.moph.go.th/odpc9/forecast_detail.php?publish=12452. Accessed 15 January 2023. (in Thai)
Thairathonline. 2023. Korat Sky Clears, PM2.5 Dust Levels Decrease, Mainly Caused by Forest Fires in the National Park. https://www.thairath.co.th/news/local/northeast/2627065. Accessed 20 February 2023. (in Thai)
Sukkasem, I. 2020. Forecasting the amount of particulate matter having a diameter of less than 2.5 micrometers (PM2.5) in Nakhon Ratchasima province. The Office of Disease Prevention and Control 9 Nakhon Rathasima Journal. 27(1): 16-25. (in Thai)
Sangsri, P. and Chaiwuttisak, P. 2021. Hybrid of neural network and Markov chain method for predicting PM2.5 concentrations. Thai Science and Technology Journal. 29(5): 752-765. (in Thai)
Amnuaylojaroen, T. 2022. Prediction of PM2.5 in an urban area of northern Thailand using multivariate linear regression model. Advances in Meteorology. 2022: 3190484.
Kumharn, W. and et al. 2022. Improved hourly and long-term PM2.5 prediction modeling based on MODIS in Bangkok. Remote Sensing Applications: Society and Environment. 28: 100864.
Saiohai, J. and et al. 2023. Statistical PM2.5 prediction in an urban area using vertical meteorological factors. Atmosphere. 14(3): 589.
Masood, A. and Ahmad, K. 2020. A model for particulate matter (PM2. 5) prediction for Delhi based on machine learning approaches. Procedia Computer Science. 167: 2101-2110.
Sobri, M.N. and et al. 2021. Predicting particulate matter (PM2.5) in Malaysia using multiple linear regression and artificial neural network. Journal of Physics: Conference Series. 2084: 012010.
Hyndman, R.J. and Athanasopoulos, G. 2021. Forecasting: Principles and Practice. 3rd edition. Melbourne: OTexts.
Hair, J.F. and et al. 2009. Multivariate Data Analysis. 7th edition. New York: Pearson.
Han, J., Kamber, M. and Pei, J. 2012. Data Mining: Concepts and Techniques. Amsterdam: Elsevier.
Pasilatetsang, B. 2021. Creating Learning for AI with Python Machine Learning. Bangkok: V. Print (1991) Co., Ltd. (in Thai)
Pollution Control Department. 2022. Historical Air Quality Data. http://air4thai.pcd.go.th/webV3/#/History. Accessed 1 October 2022. (in Thai)
Northeastern Meteorological Center (Lower Part). 2022. Request Online Data. http://www.ubonmet.tmd.go.th/. Accessed 1 October 2022. (in Thai)
Pollution Control Department. 2023. Air Quality Index. http://air4thai.pcd.go.th/webV3/#/AQIInfo. Accessed 15 October 2023. (in Thai)
