Extreme Value Model to Forecast PM2.5 Concentration Through a Non-Stationary Process
Downloads
The objectives of this research were to develop a model to forecast and estimate the return levels for daily maximum PM2.5 concentrations in Thailand, applying Extreme Value Theory (EVT) with the Generalized Extreme Value (GEV) distribution under eight models for stationary and non-stationary process. This research utilized reanalysis data from the NASA EARTHDATA satellite, represented as grid points with a spatial resolution of 50 × 62.5 km, enabling the analysis of daily maximum PM2.5 concentrations across 176 grid points from January 1, 2009 to October 31, 2024. The analysis revealed that Model 2 (μ(t)=β0+β1t where σ and ξ are constants) is the most suitable model for five grid points, namely Sa Kaeo Province, Uthai Thani Province, Nakhon Ratchasima Province, Bueng Kan Province and Mae Hong Son Province, whereas Model 1 (μ, σ and ξ are constants) is suitable for the remaining 171 grid points. Estimating the return levels for return periods of 5, 10, 25, and 50 years showed that Northern Thailand had the most extreme daily PM2.5 concentrations, for all return periods especially Mae Hong Son Province. The results of this analysis can serve as valuable information to support decision-making for response planning in high-risk areas, aiding in efficient resource allocation and preventive measures.
Downloads
[1] Sudumbrekar, A., Kale, R., Kaurwar, T., Mule, V., & Devkar, A. (2021). Feasibility Study of ARIMA Model for PM2.5 Prediction using Real-world Data Gathered from Pune Region. New Frontiers in Communication and Intelligent Systems, 105–111, SCRS Publication, Delhi, India. doi:10.52458/978-81-95502-00-4-13.
[2] Zhao, L., Li, Z., & Qu, L. (2022). Forecasting of Beijing PM2.5 with a hybrid ARIMA model based on integrated AIC and improved GS fixed-order methods and seasonal decomposition. Heliyon, 8(12), 12239. doi:10.1016/j.heliyon.2022.e12239.
[3] Sudha, G., & Suguna, S. (2022). Health Hazard: PM2. 5 Forecast-A Visual Analytic Framework Using ARIMA. International journal of health sciences, 6(S2), 630-642. doi:10.53730/ijhs.v6nS2.5066.
[4] Amelia, R., Guskarnali, Mahardika, R. G., Niani, C. R., & Lewaherilla, N. (2022). Predicting particulate matter PM2.5 using the exponential smoothing and Seasonal ARIMA with R studio. IOP Conference Series: Earth and Environmental Science, 1108(1), 012079. doi:10.1088/1755-1315/1108/1/012079.
[5] Wang, M., Zhang, Q., Tai, C., Li, J., Yang, Z., Shen, K., & Guo, C. (2022). Design of PM2.5 monitoring and forecasting system for opencast coal mine road based on internet of things and ARIMA Mode. PLOS ONE, 17(5), e0267440. doi:10.1371/journal.pone.0267440.
[6] Duan, J., Gong, Y., Luo, J., & Zhao, Z. (2023). Air-quality prediction based on the ARIMA-CNN-LSTM combination model optimized by dung beetle optimizer. Scientific Reports, 13(1), 12127. doi:10.1038/s41598-023-36620-4.
[7] Hernández-Medina, D. S., Zafra-Mejía, C. A., & Rondón-Quintana, H. A. (2024). ARIMA Analysis of PM Concentrations during the COVID-19 Isolation in a High-Altitude Latin American Megacity. Atmosphere, 15(6), 683. doi:10.3390/atmos15060683.
[8] Pyae, T. S., & Kallawicha, K. (2024). First temporal distribution model of ambient air pollutants (PM2.5, PM10, and O3) in Yangon City, Myanmar during 2019–2021. Environmental Pollution, 347, 123718. doi:10.1016/j.envpol.2024.123718.
[9] Gao, W., Xiao, T., Zou, L., Li, H., & Gu, S. (2024). Analysis and Prediction of Atmospheric Environmental Quality Based on the Autoregressive Integrated Moving Average Model (ARIMA Model) in Hunan Province, China. Sustainability (Switzerland), 16(19), 8471. doi:10.3390/su16198471.
[10] Mahawan, N., Charoentrakulpeeti, W., & Knobnob, N. (2024). A Situation and Temporal Behaviors of Air Pollution by ARIMA Model: A Case Study of Chiang Mai. Asian Creative Architecture, Art and Design, 37(1), 1–16. doi:10.55003/acaad.2024.268045.
[11] Sharma, V., Ghosh, S., Mishra, V. N., & Kumar, P. (2025). Spatio-temporal Variations and Forecast of PM2.5 concentration around selected Satellite Cities of Delhi, India using ARIMA model. Physics and Chemistry of the Earth, 138, 103849. doi:10.1016/j.pce.2024.103849.
[12] Abuouelezz, W., Ali, N., Aung, Z., Altunaiji, A., Shah, S. B., & Gliddon, D. (2025). Exploring PM2.5 and PM10 ML forecasting models: a comparative study in the UAE. Scientific Reports, 15(1), 9797. doi:10.1038/s41598-025-94013-1.
[13] Nourmohammad, E., & Rashidi, Y. (2025). Ground data analysis for PM2.5 Prediction using predictive modeling techniques. Journal of Air Pollution and Health, 10(1), 61–82. doi:10.18502/japh.v10i1.18095.
[14] Pornsopin, J., Busababodhin, P., Phoophiwfa, T., Chiangpradit, M., & Guayjarernpanishk, P. (2021). Risk analysis of PM2.5 and PM10: A case study at Khon Kaen City. The Journal of Applied Science, 20(2), 157–172. doi:10.14416/j.appsci.2021.02.012.
[15] Intarapak, S., & Supapakorn, T. (2021). Investigation on the Statistical Distribution of PM2.5 Concentration in Chiang Mai, Thailand. WSEAS Transactions on Environment and Development, 17, 1219–1227. doi:10.37394/232015.2021.17.111.
[16] Bodhisuwan, W., & Aryuyuen, S. (2022). The Poisson-Transmuted Janardan Distribution for Modelling Count Data. Trends in Sciences, 19(5), 1450–1461. doi:10.48048/tis.2022.2898.
[17] Aguirre-Salado, A. I., Venancio-Guzmán, S., Aguirre-Salado, C. A., & Santiago-Santos, A. (2022). A Novel Tree Ensemble Model to Approximate the Generalized Extreme Value Distribution Parameters of the PM2.5 Maxima in the Mexico City Metropolitan Area. Mathematics, 10(12), 2056. doi:10.3390/math10122056.
[18] Peter, A. E., Raj, M., Gangadharan, P., Athira, P., & Nagendra, S. M. S. (2023). Trends, Extreme Events and Long-term Health Impacts of Particulate Matter in a Southern Indian Industrial Area. Water, Air, and Soil Pollution, 234(5), 303. doi:10.1007/s11270-023-06302-y.
[19] Yang, H. C., Yang, M. C., Wong, G. W., & Chen, M. C. (2023). Extreme Event Discovery With Self-Attention for PM2.5 Anomaly Prediction. IEEE Intelligent Systems, 38(2), 36–45. doi:10.1109/MIS.2023.3236561.
[20] Klinjan, K., Sottiwan, T., & Aryuyuen, S. (2024). Extreme Value Analysis with New Generalized Extreme Value Distributions: A Case Study for Risk Analysis on Pm2.5 and Pm10 in Pathum Thani, Thailand. Communications in Mathematical Biology and Neuroscience, 100. doi:10.28919/cmbn/8833.
[21] Vazquez-Morales, J. A., Rodrigues, E. R., & Reyes-Cervantes, H. J. (2024). Bivariate Analysis of Pollutants Monthly Maxima in Mexico City Using Extreme Value Distributions and Copula. Journal of Environmental Protection, 15(07), 796–826. doi:10.4236/jep.2024.157046.
[22] Guayjarernpanishk, P., Chutiman, N., Piwpuan, N., Kong-Ied, B., & Chiangpradit, M. (2024). Air Pollution Forecasting in a Regional Context for Sustainable Management. Emerging Science Journal, 8(5), 2091-2100. doi:10.28991/ESJ-2024-08-05-024.
[23] Ghosh, D. (2025). Assessing air quality extremes: a comparative extreme value analysis of metropolitan cities across India and the world. Environmental Monitoring and Assessment, 197(3), 276. doi:10.1007/s10661-025-13754-8.
[24] Maricq, M. M., & Bishop, G. A. (2025). Extreme value theory analysis of high emitter trends across four US cities from 1995 to 2021. Science of the Total Environment, 958. doi:10.1016/j.scitotenv.2024.177873.
[25] Jenkinson, A. F. (1955). The frequency distribution of the annual maximum (or minimum) values of meteorological elements. Quarterly Journal of the Royal Meteorological Society, 81(348), 158–171. doi:10.1002/qj.49708134804.
[26] Brockett, P. L., & Galambos, J. (1980). The Asymptotic Theory of Extreme Order Statistics. Journal of the American Statistical Association, 75(370), 473. doi:10.2307/2287487.
[27] W.H.O. (2021). WHO global air quality guidelines: Particulate matter (PM2.5 and PM10), ozone, nitrogen dioxide, sulfur dioxide and carbon monoxide. World Health Organization (WHO), Geneva, Switzerland.
- This work (including HTML and PDF Files) is licensed under a Creative Commons Attribution 4.0 International License.
