Volodymyr Hura

Modelling and Intellectual Analysis of Quantitative Characteristics of Air Pollution

PDF (511KB), PP.263-273

Views: 0 Downloads: 0

Author(s)

1. Department of Radioelectronic and Computer Systems, Faculty of Electronics and Computer Technologies, Ivan Franko National University of Lviv, 50 Drahomanova St., 79005 Lviv, Ukraine

* Corresponding author.

DOI: https://doi.org/10.5815/ijem.2026.04.18

Received: 29 Apr. 2026 / Revised: 8 Jun. 2026 / Accepted: 10 Jul. 2026 / Published: 8 Aug. 2026

Index Terms

Air pollution, modeling, intelligent data analysis, machine learning, neural networks, forecasting, software-hardware complex, monitoring, cloud technologies

Abstract

The current state of environmental safety requires the introduction of the latest technologies for monitoring and analyzing environmental data. Air pollution with fine particles (PM2.5, PM10) from local emission sources creates significant computational challenges due to insufficient data and the dynamic nature of pollution propagation processes.
Objective. The goal of the work is to solve these problems by developing and integrating modern methods and tools for modeling and intelligent analysis of air pollution characteristics. A prototype hybrid algorithmic pipeline is proposed that integrates an adapted Gaussian model with optimized machine learning and neural network models. The method utilizes a Mamdani-type fuzzy logic system to determine the Atmospheric Stability Class based on continuous meteorological inputs. Additionally, Bayesian inverse modeling using Markov Chain Monte Carlo (MCMC) methods is applied to estimate unknown source emission intensity. The approach is implemented using cloud technologies (Azure Data Lake) and edge computing systems (Nvidia Jetson Nano). A large-scale comparative analysis of deep neural network architectures (Bidirectional LSTM, CNN) and ensemble models (XGBoost, CatBoost) was conducted. The Bidirectional LSTM provided the best overall performance (MSE=0.521, R2=0.985). The integration of fuzzy stability inputs reduced the MSE by 16%. The experiments conducted and numerical modeling confirmed the effectiveness of the proposed methods and the operability of the developed neuro-controller system. The results allow recommending the integrated approach for real-time environmental monitoring and decision support in data-scarce environments.

Cite This Paper

Volodymyr Hura, "Modelling and Intellectual Analysis of Quantitative Characteristics of Air Pollution", International Journal of Engineering and Manufacturing (IJEM), Vol.16, No.4, pp.263-273, 2026. DOI:10.5815/ijem.2026.04.18

Reference

[1]Seinfeld, J. H., Pandis, S. N. (2016). Atmospheric Chemistry and Physics: From Air Pollution to Climate Change (3rd ed.). John Wiley Sons.
[2]Hanna, S. R., Briggs, G. A., Hosker, R. P. Jr. (1982). Handbook on Atmospheric Diffusion. DOE/TIC-11223. U.S. Department of Energy.
[3]X., et al. (2024). "A Physics-Informed Multimodal Deep Learning Framework for City-Scale Air-Quality and Health-Risk Prediction." MDPI Systems, 14(3), 320.
[4]Inam, et al. (2025). "A Transformer-Based Framework for Accurate and Interpretable PM2.5 Forecasting through Integration of Country-Level Embeddings and Explainable AI." The Asian Bulletin of Big Data Management, 5(3), 245-255. https://www.researchgate.net/publication/395695149
[5]Wang, Y., et al. (2024). "Evaluating deep learning time series models for PM2.5 forecasting across diverse horizons." Scientific Reports / PMC, PMC12907896. https://pmc.ncbi.nlm.nih.gov/articles/PMC12907896/
[6]Liang, Y., et al. (2024). "Spatio-Temporal Field Neural Networks for Air Quality Inference." Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2024. https://www.ijcai.org/proceedings/2024/0803.pdf
[7]Zhao, Z., et al. (2024). "Air quality index prediction based on spatio-temporal graph neural networks: An empirical study of Xi'an, China." Engineering Applications of Artificial Intelligence, 166:113547.b https://www.researchgate.net/publication/400324948
[8]Kumar, S., et al. (2024). "Lightweight Deep Learning Models for Real-Time PM2.5 Forecasting in Resource-Constrained Edge IoT Devices." IEEE Internet of Things Journal, 11(8), 14502-14515. https://arxiv.org/html/2511.21857v1
[9]Zhang, L., et al. (2024). "Air quality forecasting using Bidirectional LSTM and environmental covariates." Atmospheric Environment, 312, 120023. https://doi.org/10.1016/j.atmosenv.2023.120023
[10]Chen, J., et al. (2023). "Bayesian inverse modeling for estimating point source emissions using Markov Chain Monte Carlo methods." Environmental Modelling & Software, 160, 105580. https://doi.org/10.1016/j.envsoft.2022.105580
[11]Singh, A., et al. (2024). "Fuzzy logic-based atmospheric stability classification for urban and rural dispersion modeling." Science of The Total Environment, 908, 168340. https://doi.org/10.1016/j.scitotenv.2023.168340
[12]Liu, Y., et al. (2025). "Edge-cloud collaborative framework for real-time PM2.5 monitoring and prediction." IEEE Internet of Things Journal, 12(2), 1500-1512. https://doi.org/10.1109/JIOT.2024.3312098
[13]Patel, R., et al. (2023). "Evaluating tree-based ensemble algorithms for predictive modeling of particulate matter: A comparative study of XGBoost, LightGBM, and CatBoost." Ecological Informatics, 75, 102011. https://doi.org/10.1016/j.ecoinf.2023.102011
[14]Wu, H., et al. (2024). "Gaussian plume dispersion coupled with machine learning for accurate industrial and local emission tracking." Journal of Environmental Management, 345, 118502. https://doi.org/10.1016/j.jenvman.2023.118502
[15]Hura, V., Monastyrskyi, L. (2023). Using cloud technologies for air quality analysis and monitoring. Electronics and Information Technologies, (24), 34–45. https://doi.org/10.30970/eli.24.4
[16]Hura, V., Monastyrskyi, L. (2023). IOT solution for air quality monitoring using ESP32. Artificial Intelligence, (97), 86–93. https://doi.org/10.15407/jai2023.03.086

International Journal of Engineering and Manufacturing (IJEM)