Spatial–temporal approaches for PM2.5 concentration prediction: a review

  • Hemant N Patel Computer Engineering, Sankalchand Patel College of Engineering, Sankalchand Patel University, Visnagar, India
DOI https://doi.org/10.55670/fpll.fer.2.1.2
0 Abstract Views 0 Downloads
Abstract

PM pollution has become a major environmental concern due to its adverse effects on air quality and human health. Accurate concentration prediction is essential for understanding pollution patterns and supporting effective air quality management. This paper examines statistical analysis, machine learning (ML), deep learning (DL), and data-driven forecasting as spatiotemporal approaches for predicting PM₂.₅ concentrations. Trends in pollution data over time can be identified using statistical models like ARIMA and linear regression. To understand the complex interplay between pollution levels, weather, and other environmental variables, ML techniques have proven highly effective. Transformers, recurrent neural networks, and convolutional neural networks (CNNs) are examples of DL architectures that can learn to extract spatial patterns and capture temporal dependencies across regions and time. The review also discusses spatial–temporal relationships, including autocorrelation, spatial heterogeneity, and cross-region prediction challenges. Ground-based monitoring stations, meteorological observations, reanalysis datasets, and satellite remote sensing provide important inputs for model development. Furthermore, inconsistent spatiotemporal resolution, uneven monitoring station distribution, and missing data remain significant challenges. This study provides a concise overview of current prediction methods, data needs, and practical constraints to support the development of trustworthy spatiotemporal PM₂.₅ forecasting systems and enhanced air quality monitoring.

Graphical Abstract
Keywords
PM₂.₅ prediction Spatial–temporal analysis Air quality forecasting Machine learning Deep learning Air pollution
How to Cite
N Patel, H. . (2026). Spatial–temporal approaches for PM2.5 concentration prediction: a review. Future Engineering Research, 2(1), 19–26. https://doi.org/10.55670/fpll.fer.2.1.2
References
  1. R. A. Sowah and C. M. Afemeku, “Temporal and Spatial Analysis of PM2.5 Concentrations in Accra Using Integrated Ground-Based and Satellite Sensor Data,” Aug. 12, 2024. doi: 10.21203/rs.3.rs-4841971/v1.
  2. K. Chatterjee et al., “AiM: urban air quality forecasting with grid-embedded recurrent MLP model,” 2025.
  3. D. E. Schraufnagel, “The health effects of ultrafine particles,” Exp. Mol. Med., vol. 52, no. 3, pp. 311–317, 2020, doi: 10.1038/s12276-020-0403-3.
  4. P. Thangavel, D. Park, and Y. C. Lee, “Recent Insights into Particulate Matter (PM2.5)-Mediated Toxicity in Humans: An Overview,” Int. J. Environ. Res. Public Health, vol. 19, no. 12, 2022, doi: 10.3390/ijerph19127511.
  5. K. Moloi, K. Addo, and E. Mnkandla, “Spatio-Temporal Artificial Intelligence for Multi-Hazard-Aware Renewable Energy Site Selection Using Integrated Geospatial and Climate Data,” Processes, vol. 13, no. 11, 2025, doi: 10.3390/pr13113728.
  6. R. Ameri, C.-C. Hsu, S. S. Band, M. Zamani, C.-M. Shu, and S. Khorsandroo, “Forecasting PM 2.5 concentration based on integrating of CEEMDAN decomposition method with SVM and LSTM,” Ecotoxicol. Environ. Saf., vol. 266, no. 115572, pp. 1–11, Nov. 2023, doi: 10.1016/j.ecoenv.2023.115572.
  7. P.-Y. Wong et al., “Using a land use regression model with machine learning to estimate ground level PM2.5,” Environ. Pollut., vol. 277, p. 116846, May 2021, doi: 10.1016/j.envpol.2021.116846.
  8. Q. Zhang, S. Ye, T. Ma, X. Fang, Y. Shen, and L. Ding, “Influencing factors and trend prediction of PM2.5 concentration based on STRIPAT-Scenario analysis in Zhejiang Province, China,” Environ. Dev. Sustain., vol. 25, no. 12, pp. 14411–14435, 2023, doi: 10.1007/s10668-022-02672-1.
  9. S. Fang, Q. Li, H. Karimian, H. Liu, and Y. Mo, “DESA: a novel hybrid decomposing-ensemble and spatiotemporal attention model for PM2.5 forecasting,” Environ. Sci. Pollut. Res., vol. 29, no. 36, pp. 54150–54166, 2022, doi: 10.1007/s11356-022-19574-4.
  10. X. Li et al., “Long short-term memory neural network for air pollutant concentration predictions: Method development and evaluation,” Environ. Pollut., vol. 231, pp. 997–1004, Dec. 2017, doi: 10.1016/j.envpol.2017.08.114.
  11. W. Wang and J. Gong, “New relaxation function and age-adjusted effective modulus expressions for creep analysis of concrete structures,” Eng. Struct., vol. 188, pp. 1–10, Jun. 2019, doi: 10.1016/j.engstruct.2019.03.009.
  12. I. Djalalova, L. Delle Monache, and J. Wilczak, “PM2.5 analog forecast and Kalman filter post-processing for the Community Multiscale Air Quality (CMAQ) model,” Atmos. Environ., vol. 108, pp. 76–87, May 2015, doi: 10.1016/j.atmosenv.2015.02.021.
  13. X. Feng, Q. Li, Y. Zhu, J. Hou, L. Jin, and J. Wang, “Artificial neural networks forecasting of PM2.5 pollution using air mass trajectory based geographic model and wavelet transformation,” Atmos. Environ., vol. 107, pp. 118–128, Apr. 2015, doi: 10.1016/j.atmosenv.2015.02.030.
  14. S. Zhou, W. Wang, L. Zhu, Q. Qiao, and Y. Kang, “Deep-learning architecture for PM2.5 concentration prediction: A review,” Environ. Sci. Ecotechnology, vol. 21, p. 100400, Sep. 2024, doi: 10.1016/j.ese.2024.100400.
  15. H. Xing, G. Wang, C. Liu, and M. Suo, “PM2.5 concentration modeling and prediction by using temperature-based deep belief network,” Neural Networks, vol. 133, pp. 157–165, Jan. 2021, doi: 10.1016/j.neunet.2020.10.013.
  16. L. Li et al., “Ensemble-based deep learning for estimating PM2.5 over California with multisource big data including wildfire smoke,” Environ. Int., vol. 145, p. 106143, Dec. 2020, doi: 10.1016/j.envint.2020.106143.
  17. X. Dai, J. Liu, and Y. Li, “A recurrent neural network using historical data to predict time series indoor PM2.5 concentrations for residential buildings,” Indoor Air, vol. 31, no. 4, pp. 1228–1237, Jul. 2021, doi: 10.1111/ina.12794.
  18. H. Zhou et al., “Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting,” 35th AAAI Conf. Artif. Intell. AAAI 2021, vol. 12B, pp. 11106–11115, 2021, doi: 10.1609/aaai.v35i12.17325.
  19. J. I. Jeong, R. J. Park, S.-W. Yeh, and J.-W. Roh, “Statistical predictability of wintertime PM2.5 concentrations over East Asia using simple linear regression,” Sci. Total Environ., vol. 776, p. 146059, Jul. 2021, doi: 10.1016/j.scitotenv.2021.146059.
  20. L. Zhang et al., “Trend analysis and forecast of PM2.5 in Fuzhou, China using the ARIMA model,” Ecol. Indic., vol. 95, pp. 702–710, Dec. 2018, doi: 10.1016/j.ecolind.2018.08.032.
  21. P. Wang, H. Zhang, Z. Qin, and G. Zhang, “A novel hybrid-Garch model based on ARIMA and SVM for PM 2.5 concentrations forecasting,” Atmos. Pollut. Res., vol. 8, no. 5, pp. 850–860, Sep. 2017, doi: 10.1016/j.apr.2017.01.003.
  22. H. Balogun, H. Alaka, and C. N. Egwim, “Boruta-grid-search least square support vector machine for NO2 pollution prediction using big data analytics and IoT emission sensors,” Appl. Comput. Informatics, vol. 21, no. 1–2, pp. 101–113, 2021, doi: 10.1108/ACI-04-20
  23. S. Shekhar et al., “Spatiotemporal data mining: A computational perspective,” ISPRS Int. J. Geo-Information, vol. 4, no. 4, pp. 2306–2338, 2015, doi: 10.3390/ijgi4042306.
  24. M. Xie, Z. Jiang, and A. M. Sainju, “Geographical Hidden Markov Tree for Flood Extent Mapping,” in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, in KDD ’18. New York, NY, USA, NY, USA: ACM, Jul. 2018, pp. 2545–2554. doi: 10.1145/3219819.3220053.
  25. M. Yu, A. Masrur, and C. Blaszczak-Boxe, “Predicting hourly PM2.5 concentrations in wildfire-prone areas using a SpatioTemporal Transformer model,” Sci. Total Environ., vol. 860, p. 160446, Feb. 2023, doi: 10.1016/j.scitotenv.2022.160446.
  26. A. Vaswani et al., “Attention is all you need,” in Proceedings of the 31st International Conference on Neural Information Processing Systems, in NIPS’17. Red Hook, NY, USA: Curran Associates Inc., 2017, pp. 6000–6010. doi: 10.48550/arXiv.1706.03762.
  27. C. N. Shatdarsanam, S. R. Kurakula, S. Sheshansh, B. S. Balasundram, R. A. M. Sait, and S. Katta, “Retracted: A Machine Learning-Based Approach to Real-Time Traffic Prediction using Large Language Models: Model Performance and Scalability Challenges,” in 2026 2nd International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), Greater Noida, (Delhi NCR), India: IEEE, Feb. 2026, pp. 1136–1141. doi: 10.1109/IC3ECSBHI67834.2026.11469057.
  28. C. Wu et al., “Time-Series Data-Driven PM2.5 Forecasting: From Theoretical Framework to Empirical Analysis,” Atmosphere (Basel)., vol. 16, no. 3, p. 292, Feb. 2025, doi: 10.3390/atmos16030292.
  29. G. Liu, X. Dong, Z. Kong, and K. Dong, “Does national air quality monitoring reduce local air pollution? The case of PM2.5 for China,” J. Environ. Manage., vol. 296, p. 113232, Oct. 2021, doi: 10.1016/j.jenvman.2021.113232.
  30. J. He et al., “The first high-resolution meteorological forcing dataset for land process studies over China,” Sci. Data, vol. 7, no. 1, p. 25, 2020, doi: 10.1038/s41597-020-0369-y.
  31. C. C. Crossett, A. K. Betts, L. A. L. Dupigny-Giroux, and A. Bomblies, “Evaluation of daily precipitation from the era5 global reanalysis against ghcn observations in the northeastern united states,” Climate, vol. 8, no. 12, pp. 1–14, 2020, doi: 10.3390/cli8120148.
  32. J. Wu, F. Yao, W. Li, and M. Si, “VIIRS-based remote sensing estimation of ground-level PM2.5 concentrations in Beijing–Tianjin–Hebei: A spatiotemporal statistical model,” Remote Sens. Environ., vol. 184, pp. 316–328, Oct. 2016, doi: 10.1016/j.rse.2016.07.015.
  33. W. A. Jabbar, T. Subramaniam, A. E. Ong, M. I. Shu’Ib, W. Wu, and M. A. de Oliveira, “LoRaWAN-Based IoT System Implementation for Long-Range Outdoor Air Quality Monitoring,” Internet of Things, vol. 19, p. 100540, Aug. 2022, doi: 10.1016/j.iot.2022.100540.
  34. L. Morawska, C. Asbach, and H. Patel, “Application of PM 2.5 low-cost sensors for indoor air quality compliance monitoring,” Aerosol Sci. Technol., vol. 59, no. 10, pp. 1210–1220, Oct. 2025, doi: 10.1080/02786826.2025.2457326.
  35. N. Otanasap, S. Tadsuan, and C. Chalermsuk, “An AIoT-based Air Quality Monitoring System for Real-time PM2.5 Prediction in Urban Environments,” ASEAN J. Sci. Technol. Reports, vol. 28, no. 1, p. e255168, Dec. 2024, doi: 10.55164/ajstr.v28i1.255168.
  36. Y. Liu et al., “Assessment of personal exposure to PM for multiple transportation modes,” Transp. Res. Part D Transp. Environ., vol. 101, p. 103086, Dec. 2021, doi: 10.1016/j.trd.2021.103086.
  37. Y. Yang, Z. Bai, Z. Hu, Z. Zheng, K. Bian, and L. Song, “AQNet: Fine-grained 3D spatio-temporal air quality monitoring by aerial-ground WSN,” in IEEE INFOCOM 2018 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), IEEE, Apr. 2018, pp. 1–2. doi: 10.1109/INFCOMW.2018.8406985.
  38. Q. Xiao et al., “Evaluation of gap-filling approaches in satellite-based daily PM2.5 prediction models,” Atmos. Environ., vol. 244, p. 117921, Jan. 2021, doi: 10.1016/j.atmosenv.2020.117921.
  39. G. Tang and B. Li, “Hybrid GCN Transformer Model with Transfer Learning for PM2.5 Concentration Prediction,” in 2026 5th International Conference on Electronics Technology and Artificial Intelligence (ETAI), IEEE, Mar. 2026, pp. 978–983. doi: 10.1109/ETAI68332.2026.11485473.
  40. J. Li and J. Zhao, “IF-LSTM Fusion Model for PM 2.5 Prediction and Anomaly Early Warning,” in 2026 8th International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI), IEEE, May 2026, pp. 568–571. doi: 10.1109/IoTAAI70471.2026.11607793.
  41. H. Yang, Z. Shu, Z. Li, J. Liu, Y. Yang, and Y. Qiu, “PM2.5 Concentration Prediction Model Based on BP Neural Network Optimized by Integrated Black-winged Kite Algorithm,” in 2025 5th International Symposium on Computer Technology and Information Science (ISCTIS), IEEE, May 2025, pp. 298–302. doi: 10.1109/ISCTIS65944.2025.11065930.
  42. J. Geng, L. Li, Y. Yan, and Y. Zhang, “MDC-STGformer: Multi-scale Dilated Convolution Enhanced Spatio-Temporal Graph Transformer for PM2.5 Concentration Prediction,” in 2025 6th International Conference on Machine Learning and Computer Application (ICMLCA), IEEE, Oct. 2025, pp. 337–341. doi: 10.1109/ICMLCA66850.2025.11336538.
  43. H. Cheng and H. Fan, “PM2.5 Concentration Hourly Multi-Step Prediction Using Spatial-Temporal Synchronous Graph Convolution Network,” in IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, IEEE, Jul. 2024, pp. 5727–5731. doi: 10.1109/IGARSS53475.2024.10640613.
  44. T. Pham and H. D. Thi, “PM2.5 Concentration Prediction Using Signal Decomposition and Long-short Term Memory Network,” in 2024 9th International Conference on Applying New Technology in Green Buildings (ATiGB), IEEE, Aug. 2024, pp. 135–140. doi: 10.1109/ATiGB63471.2024.10717808.
  45. H. Hu, Y. Ma, and Z. Zhou, “Short-Term PM2.5 Concentration Prediction Based on CEEMD and LSTM Model,” in 2023 2nd International Conference on Artificial Intelligence and Autonomous Robot Systems (AIARS), IEEE, Jul. 2023, pp. 82–86. doi: 10.1109/AIARS59518.2023.00023.