Integrating Temporal Analysis with Hybrid Machine Learning and Deep Learning Models for Enhanced Air Quality Prediction

Muhammad Omer; Sardar Jaffar Ali; Syed M. Raza; Duc Tai Le; Hyunseung Choo

doi:10.1109/IMCOM64595.2025.10857575

Integrating Temporal Analysis with Hybrid Machine Learning and Deep Learning Models for Enhanced Air Quality Prediction

Muhammad Omer
, Sardar Jaffar Ali
, Syed M. Raza
, Duc Tai Le
, Hyunseung Choo

Department of Computer Science and Engineering

Sungkyunkwan University
University of Glasgow

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Air pollution remains a critical issue, adversely affecting public health and the environment. In this study, we utilize the Air Quality index dataset from Kaggle to analyze temporal and seasonal variations of key pollutants, specifically Carbon Monoxide (CO), Nitrogen Oxides (NOx), and Benzene (C₆H₆ ). Building upon this analysis, we predict Absolute Humidity (AH), a vital meteorological factor influencing pollutant dispersion, using Machine Learning (ML) and Deep Learning (DL) techniques. Three ML techniques, Linear Regression (LR), Random Forest (RF), and Support Vector Regression (SVR), and three DL techniques, Artificial Neural Network (ANN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), are employed for predicting AH. The results indicate that while the RF model achieved the lowest Mean Absolute Error (MAE) among ML methods (0.02), the CNN model, despite having an MAE of 0.04, demonstrated statistical superiority through paired t-tests and Wilcoxon signed-rank tests (p < 0.005), outperforming RF (p < 0.03). These findings highlight the statistical significance of DL methods, specifically CNN, over ML methods in predicting AH.

Original language	English
Title of host publication	Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025
Editors	Sukhan Lee, Hyunseung Choo, Roslan Ismail
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798331507817
DOIs	https://doi.org/10.1109/IMCOM64595.2025.10857575
State	Published - 2025
Event	19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025 - Bangkok, Thailand Duration: 3 Jan 2025 → 5 Jan 2025

Publication series

Name	Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

Conference

Conference	19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025
Country/Territory	Thailand
City	Bangkok
Period	3/01/25 → 5/01/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Absolute Humidity
Benzene
Carbon Monoxide
Nitrogen Oxide
Wilcoxon signed-rank tests
paired T-tests

Access to Document

10.1109/IMCOM64595.2025.10857575

Cite this

Omer, M., Ali, S. J., Raza, S. M., Le, D. T., & Choo, H. (2025). Integrating Temporal Analysis with Hybrid Machine Learning and Deep Learning Models for Enhanced Air Quality Prediction. In S. Lee, H. Choo, & R. Ismail (Eds.), Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025 (Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IMCOM64595.2025.10857575

Omer, Muhammad ; Ali, Sardar Jaffar ; Raza, Syed M. et al. / Integrating Temporal Analysis with Hybrid Machine Learning and Deep Learning Models for Enhanced Air Quality Prediction. Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025. editor / Sukhan Lee ; Hyunseung Choo ; Roslan Ismail. Institute of Electrical and Electronics Engineers Inc., 2025. (Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025).

@inproceedings{503c8390309d4f72ac95fbd3783918f8,

title = "Integrating Temporal Analysis with Hybrid Machine Learning and Deep Learning Models for Enhanced Air Quality Prediction",

abstract = "Air pollution remains a critical issue, adversely affecting public health and the environment. In this study, we utilize the Air Quality index dataset from Kaggle to analyze temporal and seasonal variations of key pollutants, specifically Carbon Monoxide (CO), Nitrogen Oxides (NOx), and Benzene (C6H6 ). Building upon this analysis, we predict Absolute Humidity (AH), a vital meteorological factor influencing pollutant dispersion, using Machine Learning (ML) and Deep Learning (DL) techniques. Three ML techniques, Linear Regression (LR), Random Forest (RF), and Support Vector Regression (SVR), and three DL techniques, Artificial Neural Network (ANN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), are employed for predicting AH. The results indicate that while the RF model achieved the lowest Mean Absolute Error (MAE) among ML methods (0.02), the CNN model, despite having an MAE of 0.04, demonstrated statistical superiority through paired t-tests and Wilcoxon signed-rank tests (p < 0.005), outperforming RF (p < 0.03). These findings highlight the statistical significance of DL methods, specifically CNN, over ML methods in predicting AH.",

keywords = "Absolute Humidity, Benzene, Carbon Monoxide, Nitrogen Oxide, Wilcoxon signed-rank tests, paired T-tests",

author = "Muhammad Omer and Ali, \{Sardar Jaffar\} and Raza, \{Syed M.\} and Le, \{Duc Tai\} and Hyunseung Choo",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025 ; Conference date: 03-01-2025 Through 05-01-2025",

year = "2025",

doi = "10.1109/IMCOM64595.2025.10857575",

language = "English",

series = "Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Sukhan Lee and Hyunseung Choo and Roslan Ismail",

booktitle = "Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025",

}

Omer, M, Ali, SJ, Raza, SM, Le, DT & Choo, H 2025, Integrating Temporal Analysis with Hybrid Machine Learning and Deep Learning Models for Enhanced Air Quality Prediction. in S Lee, H Choo & R Ismail (eds), Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025. Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025, Institute of Electrical and Electronics Engineers Inc., 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025, Bangkok, Thailand, 3/01/25. https://doi.org/10.1109/IMCOM64595.2025.10857575

Integrating Temporal Analysis with Hybrid Machine Learning and Deep Learning Models for Enhanced Air Quality Prediction. / Omer, Muhammad; Ali, Sardar Jaffar; Raza, Syed M. et al.
Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025. ed. / Sukhan Lee; Hyunseung Choo; Roslan Ismail. Institute of Electrical and Electronics Engineers Inc., 2025. (Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Integrating Temporal Analysis with Hybrid Machine Learning and Deep Learning Models for Enhanced Air Quality Prediction

AU - Omer, Muhammad

AU - Ali, Sardar Jaffar

AU - Raza, Syed M.

AU - Le, Duc Tai

AU - Choo, Hyunseung

PY - 2025

Y1 - 2025

N2 - Air pollution remains a critical issue, adversely affecting public health and the environment. In this study, we utilize the Air Quality index dataset from Kaggle to analyze temporal and seasonal variations of key pollutants, specifically Carbon Monoxide (CO), Nitrogen Oxides (NOx), and Benzene (C6H6 ). Building upon this analysis, we predict Absolute Humidity (AH), a vital meteorological factor influencing pollutant dispersion, using Machine Learning (ML) and Deep Learning (DL) techniques. Three ML techniques, Linear Regression (LR), Random Forest (RF), and Support Vector Regression (SVR), and three DL techniques, Artificial Neural Network (ANN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), are employed for predicting AH. The results indicate that while the RF model achieved the lowest Mean Absolute Error (MAE) among ML methods (0.02), the CNN model, despite having an MAE of 0.04, demonstrated statistical superiority through paired t-tests and Wilcoxon signed-rank tests (p < 0.005), outperforming RF (p < 0.03). These findings highlight the statistical significance of DL methods, specifically CNN, over ML methods in predicting AH.

AB - Air pollution remains a critical issue, adversely affecting public health and the environment. In this study, we utilize the Air Quality index dataset from Kaggle to analyze temporal and seasonal variations of key pollutants, specifically Carbon Monoxide (CO), Nitrogen Oxides (NOx), and Benzene (C6H6 ). Building upon this analysis, we predict Absolute Humidity (AH), a vital meteorological factor influencing pollutant dispersion, using Machine Learning (ML) and Deep Learning (DL) techniques. Three ML techniques, Linear Regression (LR), Random Forest (RF), and Support Vector Regression (SVR), and three DL techniques, Artificial Neural Network (ANN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), are employed for predicting AH. The results indicate that while the RF model achieved the lowest Mean Absolute Error (MAE) among ML methods (0.02), the CNN model, despite having an MAE of 0.04, demonstrated statistical superiority through paired t-tests and Wilcoxon signed-rank tests (p < 0.005), outperforming RF (p < 0.03). These findings highlight the statistical significance of DL methods, specifically CNN, over ML methods in predicting AH.

KW - Absolute Humidity

KW - Benzene

KW - Carbon Monoxide

KW - Nitrogen Oxide

KW - Wilcoxon signed-rank tests

KW - paired T-tests

UR - https://www.scopus.com/pages/publications/85218148494

U2 - 10.1109/IMCOM64595.2025.10857575

DO - 10.1109/IMCOM64595.2025.10857575

M3 - Conference contribution

AN - SCOPUS:85218148494

T3 - Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

BT - Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

A2 - Lee, Sukhan

A2 - Choo, Hyunseung

A2 - Ismail, Roslan

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

Y2 - 3 January 2025 through 5 January 2025

ER -

Omer M, Ali SJ, Raza SM, Le DT, Choo H. Integrating Temporal Analysis with Hybrid Machine Learning and Deep Learning Models for Enhanced Air Quality Prediction. In Lee S, Choo H, Ismail R, editors, Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025. Institute of Electrical and Electronics Engineers Inc. 2025. (Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025). doi: 10.1109/IMCOM64595.2025.10857575

Integrating Temporal Analysis with Hybrid Machine Learning and Deep Learning Models for Enhanced Air Quality Prediction

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this