Authors : Napatsorn Songsangka

Volume/Issue : Volume 11 - 2026, Issue 8 - August

Google Scholar : https://tinyurl.com/ystpcu4j

DOI : https://doi.org/10.38124/ijisrt/26aug1128

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Dense particulate-matter (PM) monitoring has become increasingly practical through the proliferation of lowcost optical sensing devices; however, resolving the three health-critical size fractions—PM10, PM2.5, and PM1.0— conventionally requires either multi-channel sensory hardware or separate dedicated predictive models for each fraction, thereby inflating hardware expenses and edge computational burdens. This work establishes a single-input virtual PM sensing architecture where a single low-cost PM2.5 channel concurrently forecasts all three particulate fractions. Because PM1.0, PM2.5, and PM10 constitute a nested physical size hierarchy with tightly coupled atmospheric kinetics, their shared underlying dynamics can be effectively modeled via a unified architecture producing three simultaneous outputs in a single forward pass, eliminating redundant multi-model pipelines.

Keywords : Particulate Matter Forecasting, Multi-Task Learning, Virtual Sensor, TinyML, Edge Inference, ESP32-S3, Air Quality Monitoring, Bangkok Metropolitan Region, Chulalongkorn University.

References :

1. World Health Organization, "Ambient (outdoor) air pollution," WHO Fact Sheet, Geneva, Switzerland, 2024.
2. World Health Organization, "WHO Global Air Quality Guidelines: Particulate Matter, Ozone, Nitrogen Dioxide, Sulfur Dioxide and Carbon Monoxide," World Health Organization, Geneva, Switzerland, 2021.
3. C. Terzano, F. Di Stefano, V. Conti, E. Graziani, and A. Petroianni, "Air pollution ultrafine particles: toxicity beyond the lung," Eur. Rev. Med. Pharmacol. Sci., vol. 14, pp. 809–821, 2010.
4. D. E. Schraufnagel, "The health effects of ultrafine particles," Exp. Mol. Med., vol. 52, pp. 311–317, 2020.
5. Pollution Control Department (PCD), Thailand Ministry of Natural Resources and Environment, "Air Quality and Noise Situation in Thailand," PCD Annual Environmental Report, Bangkok, Thailand, 2024.
6. W. Phairuang, M. Hata, and M. Furuuchi, "Influence of agricultural burning and traffic emissions on fine and ultrafine particles in Bangkok, Thailand," Atmos. Environ., vol. 217, p. 116949, 2019.
7. S. ChooChuay, S. Pongpiachan, et al., "Long-term monitoring of PM2.5 and associated polycyclic aromatic hydrocarbons in the Bangkok Metropolitan Region," Aerosol Air Qual. Res., vol. 20, no. 6, pp. 1312–1324, 2020.
8. P. Srimuruganandam and K. Srichandr, "Machine learning approaches for urban PM2.5 concentration forecasting: A case study of Bangkok Metropolitan Area," Urban Clim., vol. 45, p. 101260, 2022.
9. H. Karimian, Q. Li, C. Wu, Y. Qi, Y. Mo, G. Chen, X. Zhang, and S. Sachdeva, "Evaluation of different machine learning approaches to forecasting PM2.5 mass concentrations," Aerosol Air Qual. Res., vol. 19, pp. 1400–1410, 2019.
10. F. Xiao, M. Yang, H. Fan, G. Fan, and M. A. A. Al-qaness, "An improved deep learning model for predicting daily PM2.5 concentration," Sci. Rep., vol. 10, p. 20988, 2020.
11. X. Li, L. Peng, Y. Hu, J. Shao, and T. Chi, "Deep learning architecture for air quality predictions," Environ. Sci. Pollut. Res., vol. 23, pp. 22408–22417, 2016.
12. X. Bai, N. Zhang, X. Cao, and W. Chen, "Prediction of PM2.5 concentration based on a CNN-LSTM neural network algorithm," PeerJ, vol. 12, p. e17811, 2024.
13. C. J. Huang and P. H. Kuo, "A deep cnn-lstm model for particulate matter (Pm2.5) forecasting in smart cities," Sensors, vol. 18, p. 2220, 2018.
14. S. Zhou, W. Wang, L. Zhu, Q. Qiao, and Y. Kang, "Deep-learning architecture for PM2.5 concentration prediction: A review," Environ. Sci. Ecotechnol., vol. 21, p. 100400, 2024.
15. N. Zaini, L. W. Ean, A. N. Ahmed, and M. A. Malek, "A systematic literature review of deep learning neural network for time series air quality forecasting," Environ. Sci. Pollut. Res., vol. 29, 2022.
16. T. Li, M. Hua, and X. Wu, "A Hybrid CNN-LSTM Model for Forecasting Particulate Matter (PM2.5)," IEEE Access, vol. 8, pp. 26933–26940, 2020.
17. S. Masmoudi, H. Elghazel, D. Taieb, O. Yazar, and A. Kallel, "A machine-learning framework for predicting multiple air pollutants' concentrations via multi-target regression and feature selection," Sci. Total Environ., vol. 715, 2020.
18. B. Wang, Z. Yan, J. Lu, G. Zhang, and T. Li, "Deep Multi-task Learning for Air Quality Prediction," in Proc. 25th Int. Conf. Neural Information Processing (ICONIP), 2018, pp. 93–103.
19. Z. A. Xie, C. O. Chow, J. H. Chuah, and W. J. K. Raymond, "Multi-pollutant air quality forecasting using bidirectional attention and multi-scale temporal networks," Front. Environ. Sci., vol. 13, 2025.
20. J. Song and M. E. J. Stettler, "A novel multi-pollutant space-time learning network for air pollution inference," Sci. Total Environ., vol. 811, 2022.
21. Z. Zhou, X. Chen, E. Li, L. Zeng, K. Luo, and J. Zhang, "Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing," Proc. IEEE, vol. 107, pp. 1738–1762, 2019.
22. G. H. Hong, T. C. Le, J. W. Tu, C. Wang, S. C. Chang, J. Y. Yu, G. Y. Lin, S. G. Aggarwal, and C. J. Tsai, "Long-term evaluation and calibration of three types of low-cost PM2.5 sensors at different air quality monitoring stations," J. Aerosol Sci., vol. 157, 2021.
23. F. M. J. Bulot, S. J. Johnston, P. J. Basford, N. H. C. Easton, M. Apetroaie-Cristea, G. L. Foster, A. K. R. Morris, S. J. Cox, and M. Loxham, "Long-term field comparison of multiple low-cost particulate matter sensors in an outdoor urban environment," Sci. Rep., vol. 9, 2019.
24. F. M. J. Bulot, S. J. Ossont, A. K. R. Morris, P. J. Basford, N. H. C. Easton, H. L. Mitchell, G. L. Foster, S. J. Cox, and M. Loxham, "Characterisation and calibration of low-cost PM sensors at high temporal resolution to reference-grade performance," Heliyon, vol. 9, 2023.
25. BayesWitnesses, "m2cgen: Machine learning models to native code transpiler," GitHub Repository, 2023. [Online]. Available: https://github.com/BayesWitnesses/m2cgen
26. R. David, J. Duke, A. Jain, V. J. Reddi, N. Jeffries, J. Li, N. Kreeger, I. Nappier, M. Natraj, S. Regev, R. Rhodes, T. Wang, and P. Warden, "TensorFlow Lite Micro: Embedded machine learning on TinyML systems," in Proc. 4th MLSys Conf., San Jose, CA, 2021.
27. Espressif Systems, "ESP-NN: Optimized neural network functions for Espressif chipsets," GitHub Repository, 2023. [Online]. Available: https://github.com/espressif/esp-nn
28. S. Chae, J. Shin, S. Kwon, S. Lee, S. Kang, and D. Lee, "PM10 and PM2.5 real-time prediction models using an interpolated convolutional neural network," Sci. Rep., vol. 11, 2021.
29. M. Teng, S. Li, J. Xing, G. Song, J. Yang, J. Dong, X. Zeng, and Y. Qin, "24-Hour prediction of PM2.5 concentrations by combining empirical mode decomposition and bidirectional long short-term memory neural network," Sci. Total Environ., vol. 821, 2022.
30. R. Caruana, "Multitask Learning," Mach. Learn., vol. 28, pp. 41–75, 1997.
31. D. Xu, Y. Shi, I. W. Tsang, Y.-S. Ong, C. Gong, and X. Shen, "A Survey on Multi-output Learning," IEEE Trans. Neural Netw. Learn. Syst., vol. 31, pp. 2409–2429, 2020.
32. V. J. Reddi, B. Plancher, S. Kennedy, L. Moroney, P. Warden, A. Agarwal, et al., "Widening Access to Applied Machine Learning with TinyML," Harv. Data Sci. Rev., vol. 4, 2022.
33. P. Warden and D. Situnayake, TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers, 1st ed., O'Reilly Media, Sebastopol, CA, 2019.
34. Y. Abadade, A. Temouden, H. Bamoumen, N. Benamar, Y. Chtouki, and A. S. Hafid, "A Comprehensive Survey on TinyML," IEEE Access, vol. 11, pp. 96892–96922, 2023.
35. S. S. Saha, S. S. Sandha, and M. Srivastava, "Machine Learning for Microcontroller-Class Hardware: A Review," IEEE Sens. J., vol. 22, pp. 21362–21390, 2022.
36. I. N. K. Wardana, S. A. Fahmy, and J. W. Gardner, "TinyML Models for a Low-Cost Air Quality Monitoring Device," IEEE Sens. Lett., vol. 7, 2023.
37. L. Fortuna, S. Graziani, A. Rizzo, and M. G. Xibilia, Soft Sensors for Monitoring and Control of Industrial Processes, 1st ed., Springer Science & Business Media, 2007.
38. P. Kadlec, B. Gabrys, and S. Strandt, "Data-driven Soft Sensors in the process industry," Comput. Chem. Eng., vol. 33, pp. 795–814, 2009.
39. S. De Vito, E. Esposito, M. Salvato, O. Popoola, F. Formisano, R. Jones, and G. Di Francia, "Calibrating chemical multisensory devices for real world applications: An in-depth comparison of quantitative machine learning approaches," Sens. Actuators B Chem., vol. 255, pp. 1191–1210, 2018.
40. J. Sun, J. Gong, and J. Zhou, "Estimating hourly PM2.5 concentrations in Beijing with satellite aerosol optical depth and a random forest approach," Sci. Total Environ., vol. 762, 2021.
41. S. Uttamang and V. P. Aneja, "Investigation of criteria air pollutants and aerosol characterization in Bangkok, Thailand," Environ. Sci. Atmos., vol. 3, pp. 245–258, 2023.
42. N. Thongyen and P. Sompongchaiyakul, "Spatial distribution and health risk assessment of particulate-bound toxic metals in the Bangkok urban atmosphere," Atmos. Pollut. Res., vol. 14, p. 101780, 2023.
43. K. Thepnuan, B. Yabueng, et al., "Atmospheric transport and regional dispersion of particulate matter and trace elements along the coastal zones of the Upper Gulf of Thailand," Bull. Environ. Contam. Toxicol., vol. 110, pp. 45–56, 2023.
44. C. Bergmeir and J. M. Benítez, "On the use of cross-validation for time series predictor evaluation," Inf. Sci., vol. 191, pp. 192–213, 2012.
45. P. Dejchanchaiwong and P. Tekasakul, "Characterization of carbonaceous aerosols and regional smoke haze transport in Central and Southern Thailand," Atmos. Pollut. Res., vol. 15, p. 101950, 2024.
46. W. Jinsart and K. Tamura, "Seasonal variation of PM10 and PM2.5 in Bangkok traffic corridors: Chemical composition and diurnal patterns," Chemosphere, vol. 280, p. 130640, 2021.
47. S. Wetchayont and S. Pengcheun, "Diurnal and seasonal dynamics of boundary layer meteorology and air quality in the coastal plain of Thailand," Atmos. Environ., vol. 310, p. 120010, 2024.
48. A. Kendall, Y. Gal, and R. Cipolla, "Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 7482–7491.
49. S. Shanmugavelu, M. Taillefumier, C. Culver, O. Hernandez, M. Coletti, and A. Sedova, "Impacts of floating-point non-associativity on reproducibility for HPC and deep learning applications," in Proc. SC 2024-W: Workshops Int. Conf. High Perform. Comput. Netw. Storage Anal., Atlanta, GA, USA, 2024, pp. 170–179.
50. P. Adong, E. Bainomugisha, D. Okure, and R. Sserunjogi, "Applying machine learning for large scale field calibration of low-cost PM2.5 and PM10 air pollution sensors," Appl. AI Lett., vol. 3, 2022.