Estimate Particulate Matter PM2.5 Concentration Impact of Wildfires Using Machine Learning in Chiang Mai Province, Thailand
Article Sidebar
Main Article Content
Abstract
Wildfires globally impact ecosystems, with open burning and forest fires being primary causes of air pollution. Thailand's PM2.5 levels rise annually from December to April, particularly in the central and northern regions like Chiang Mai, affecting health and the economy. However, air quality monitoring is often limited, and insufficient monitoring stations make current measurements less reliable and incongruent with the actual environmental conditions. This research directly towards assesses PM2.5 from wildfires using integrated Remote Sensing data. The Random Forest model outperformed XGBoost and CNN, with R² values of 0.74–0.91, RMSE 10.40–30.53 µg/m³, and MAPE 18.56–36.48%. On average across all stations, RF achieved R² of 0.89, RMSE 11.61 µg/m³, and MAPE 34.22%. Estimates of feature importance impacting features included AOD-MAIAC (40%), TOTEXTTAU (22%), DUSMASS25 (12%), and CO (11%), confirming wildfires and emissions drive pollution. In addition, RF spatial dynamics maps show concentration peaks in the north and south from January to April, aligned with wildfire activity, and fire heat maps confirmed PM2.5 spikes during intense wildfire periods, impacting air quality. However, due to the limited number of monitoring stations and their uneven distribution across the area, the accuracy of the data varies, leading to discrepancies at certain stations, highlighting the need for further research to improve the understanding of PM2.5 pollution. Future studies should refine RF training and incorporate additional factors to enhance model robustness for more accurate estimations.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Bisri, A. M., & Wahono, R. S. (2015). Penerapan Adaboost untuk Penyelesaian Ketidakseimbangan Kelas pada Penentuan Kelulusan Mahasiswa dengan Metode Decision Tree. Journal of intelligent systems, 1, 27–32.
Bowman, D. M. J. S., Balch, J. K., Artaxo, P., Bond, W. J., Carlson, J. M., Cochrane, M. A., D’Antonio, C. M., DeFries, R. S., Doyle, J. C., Harrison, S. P., Johnston, F. H., Keeley, J. E., Krawchuk, M. A., Kull, C. A., Marston, J. B., Moritz, M. A., Prentice, I. C., Roos, C. I., Scott, A. C., Swetnam, T. W., van der Werf, G. R., & Pyne, S. J. (2009). Fire in the Earth System. Science, 324(5926), 481-484. https://doi.org/doi:10.1126/science.1163886
Chang, X., Xing, Y., Gong, W., Yang, C., Guo, Z., Wang, D., Wang, J., Yang, H., Xue, G., & Yang, S. (2023). Evaluating gross primary productivity over 9 ChinaFlux sites based on random forest regression models, remote sensing, and eddy covariance data. Science of The Total Environment, 875, Article 162601. https://doi.org/10.1016/j.scitotenv.2023.162601
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785
ChooChuay, C., Pongpiachan, S., Tipmanee, D., Suttinun, O., Deelaman, W., Wang, Q., Xing, L., Li, G., Han, Y., & Palakun, J. (2020). Impacts of PM2. 5 sources on variations in particulate chemical compounds in ambient air of Bangkok, Thailand. Atmospheric Pollution Research, 11(9), 1657–1667.
Chudnovsky, A., Tang, C., Lyapustin, A., Wang, Y., Schwartz, J., & Koutrakis, P. (2013). A critical assessment of high resolution aerosol optical depth (AOD) retrievals for fine particulate matter (PM) predictions. Atmospheric Chemistry and Physics, 13(21), 10907–10917.
da Silva Chagas, C., de Carvalho Junior, W., Bhering, S. B., & Calderano Filho, B. (2016). Spatial prediction of soil surface texture in a semiarid region using random forest and multiple linear regressions. Catena, 139, 232–240.
Department of National Parks, Wildlife and Plant Conservation. (2023). The final report wildfire suppression statistics project 2023. https://portal.dnp.go.th/Content/firednp?contentId=15705
Di, Q., Kloog, I., Koutrakis, P., Lyapustin, A., Wang, Y., & Schwartz, J. (2016). Assessing PM2. 5 exposures with high spatiotemporal resolution across the continental United States. Environmental science & technology, 50(9), 4712–4721.
Dontree, S., Prapamontol, T., Chantara, S., & Pardthaisong, L. (2018). Smog in the North: Severity, effects, causes and solutions. Health Systems Research Institute. [in Thai]
Gelaro, R., McCarty, W., Suárez, M. J., Todling, R., Molod, A., Takacs, L., Randles, C. A., Darmenov, A., Bosilovich, M. G., & Reichle, R. (2017). The modern-era retrospective analysis for research and applications, version 2 (MERRA-2). Journal of climate, 30(14), 5419–5454.
Geng, G., Murray, N. L., Chang, H. H., & Liu, Y. (2018). The sensitivity of satellite-based PM2.5 estimates to its inputs: Implications to model development in data-poor regions. Environment International, 121, 550–560. https://doi.org/10.1016/j.envint.2018.09.051
Geo-Informatics and Space Technology Development Agency. (2023). Summary of forest fires and smog situations with satellite images. https://www.gistda.or.th/more_news.php?c_id=580&lang=TH
Giglio, L., Boschetti, L., Roy, D. P., Humber, M. L., & Justice, C. O. (2018). The Collection 6 MODIS burned area mapping algorithm and product. Remote sensing of environment, 217, 72–85.
Gu, J., Wang, Y., Ma, J., Lu, Y., Wang, S., & Li, X. (2022). An estimation method for PM2.5 based on aerosol optical depth obtained from remote sensing image processing and meteorological factors. Remote Sensing, 14(7), Article 1617. https://doi.org/10.3390/rs14071617
Inthacha, S. (2011). The climatology of Thailand and future climate change projections using the regional climate model PRECIS [Doctoral dissertation, University of East Anglia].
Jiao, L., Zhang, B., Xu, G., & Zhao, S. (2016). Spatio-temporal variability of correlation between aerosol optical depth and PM2.5 concentration. Journal of Arid Land Resources and Environment, 30, 34–39.
Junpen, A., Garivait, S., & Bonnet, S. (2013). Estimating emissions from forest fires in Thailand using MODIS active fire product and country specific data. Asia-Pacific Journal of Atmospheric Sciences, 49, 389–400.
Kanabkaew, T., & Kim Oanh, N. T. (2011). Development of spatial and temporal emission inventory for crop residue field burning. Environmental Modeling & Assessment, 16, 453–464.
Kawichai, S., Sripan, P., Rerkasem, A., Rerkasem, K., & Srisukkham, W. (2025). Long-term retrospective predicted concentration of PM2.5 in upper northern Thailand using machine learning models. Toxics, 13(3), Article 170. https://doi.org/10.3390/toxics13030170
Kirtphaiboon, S., Wongwises, P., Limsakul, A., Sooktawee, S., & Humphries, U. (2014). Rainfall variability over Thailand related to the El nino-southern oscillation (ENSO). J. Sustain. Energy Environ, 5, 37–42.
Kleist, D. T., Parrish, D. F., Derber, J. C., Treadon, R., Errico, R. M., & Yang, R. (2009). Improving incremental balance in the GSI 3DVAR analysis system. Monthly Weather Review, 137(3), 1046–1060.
Li, Y., Sha, Z., Tang, A., Goulding, K., & Liu, X. (2023). The application of machine learning to air pollution research: A bibliometric analysis. Ecotoxicology and Environmental Safety, 257, 114911. https://doi.org/10.1016/j.ecoenv.2023.114911
Lin, L., Liang, Y., Liu, L., Zhang, Y., Xie, D., Yin, F., & Ashraf, T. (2022). Estimating PM2.5 concentrations using the machine learning RF-XGBoost model in Guanzhong urban agglomeration, China. Remote Sensing, 14(20), Article 5239. https://doi.org/10.3390/rs14205239
Maurya, N. K., Pandey, P. C., Sarkar, S., Kumar, R., & Srivastava, P. K. (2022). Spatio-temporal monitoring of atmospheric pollutants using Earth observation Sentinel 5P TROPOMI data: Impact of stubble burning a case study. ISPRS International Journal of Geo-Information, 11(5), Article 301. https://doi.org/10.3390/ijgi11050301
Molod, A., Takacs, L., Suarez, M., & Bacmeister, J. (2015). Development of the GEOS-5 atmospheric general circulation model: Evolution from MERRA to MERRA2. Geoscientific Model Development, 8(5), 1339-1356.
Narita, D., Oanh, N. T. K., Sato, K., Huo, M., Permadi, D. A., Chi, N. N. H., Ratanajaratroj, T., & Pawarmart, I. (2019). Pollution Characteristics and Policy Actions on Fine Particulate Matter in a Growing Asian Economy: The Case of Bangkok Metropolitan Region. Atmosphere, 10(5), Article 227. https://doi.org/10.3390/atmos10050227
Phairuang, W., Suwattiga, P., Chetiyanukornkul, T., Hongtieab, S., Limpaseni, W., Ikemori, F., Hata, M., & Furuuchi, M. (2019). The influence of the open burning of agricultural biomass and forest fires in Thailand on the carbonaceous components in size-fractionated particles. Environmental Pollution, 247, 238–247.
Pinichka, C., Makka, N., Sukkumnoed, D., Chariyalertsak, S., Inchai, P., & Bundhamcharoen, K. (2017). Burden of disease attributed to ambient air pollution in Thailand: A GIS-based approach. PLOS ONE, 12(12), Article e0189909. https://doi.org/10.1371/journal.pone.0189909
Pollution Control Department. (2023). Report air pollution and PM2.5 concentration of Thailand 2022-2023. https://pcd.gdcatalog.go.th/dataset/air-quality-bangkok-metropolitan-region
Punsompong, P., Pani, S. K., Wang, S.-H., & Pham, T. T. B. (2021). Assessment of biomass-burning types and transport over Thailand and the associated health risks. Atmospheric Environment, 247, Article 118176. https://doi.org/10.1016/j.atmosenv.2020.118176
Rienecker, M. M., Suarez, M. J., Gelaro, R., Todling, R., Bacmeister, J., Liu, E., Bosilovich, M. G., Schubert, S. D., Takacs, L., & Kim, G.-K. (2011). MERRA: NASA’s modern-era retrospective analysis for research and applications. Journal of climate, 24(14), 3624–3648.
Rodrigues, J. A., Libonati, R., Pereira, A. A., Nogueira, J. M., Santos, F. L., Peres, L. F., Santa Rosa, A., Schroeder, W., Pereira, J. M., & Giglio, L. (2019). How well do global burned area products represent fire patterns in the Brazilian Savannas biome? An accuracy assessment of the MCD64 collections. International Journal of Applied Earth Observation and Geoinformation, 78, 318–331.
Rodriguez-Galiano, V., Mendes, M. P., Garcia-Soldado, M. J., Chica-Olmo, M., & Ribeiro, L. (2014). Predictive modeling of groundwater nitrate pollution using Random Forest and multisource variables related to intrinsic and specific vulnerability: A case study in an agricultural setting (Southern Spain). Science of the Total Environment, 476, 189–206.
Sayeed, A., Lin, P., Gupta, P., Tran, N., Buchard, V., & Chirstopher, S. (2022). Hourly and daily PM2.5 estimations using MERRA-2: A machine learning approach. Earth and Space Science Open Archive. https://doi.org/10.1002/essoar.10511086.1
Son, R., Stratoulias, D., Kim, H. C., & Yoon, J.-H. (2023, 2023/10/01/). Estimation of surface PM2.5 concentrations from atmospheric gas species retrieved from TROPOMI using deep learning: Impacts of fire on air pollution over Thailand. Atmospheric Pollution Research, 14(10), 101875. https://doi.org/https://doi.org/10.1016/j.apr.2023.101875
Thai Meteorological Department. (2023). Daily weather and meteorological report for Thailand. https://www.tmd.go.th
Wang, Y., Yuan, Q., Li, T., Tan, S., & Zhang, L. (2021). Full-coverage spatiotemporal mapping of ambient PM2.5 and PM10 over China from Sentinel-5P and assimilated datasets: Considering the precursors and chemical compositions. Science of The Total Environment, 793, Article 148535. https://doi.org/10.1016/j.scitotenv.2021.148535
Wei, J., Li, Z., Guo, J., Sun, L., Huang, W., Xue, W., Fan, T., & Cribb, M. (2019). Satellite-derived 1-km-resolution PM1 concentrations from 2014 to 2018 across China. Environmental Science & Technology, 53(22), 13265–13274.
Weichenthal, S. A., Godri Pollitt, K., & Villeneuve, P. J. (2013). PM 2.5, oxidant defence and cardiorespiratory health: A review. Environmental Health, 12, Article 49. https://doi.org/10.1186/1476-069X-12-49
Wu, W.-S., Purser, R. J., & Parrish, D. F. (2002). Three-dimensional variational analysis with spatially inhomogeneous covariances. Monthly Weather Review, 130(12), 2905–2916.
You, W., Zang, Z., Zhang, L., Li, Y., Pan, X., & Wang, W. (2016). National-scale estimates of ground-level PM2.5 concentration in China using geographically weighted regression based on 3 km resolution MODIS AOD. Remote Sensing, 8(3), Article 184. https://doi.org/10.3390/rs8030184
