A Comparative Study on Air Quality Index Prediction Using Machine Learning and Hybrid Deep Learning Models

Nemarugommula Pranav; Vishal Ganapathy; B. Geedhavarshini; Kashmira Nigade; S. Shreya; Jagalingam Pushparaj; Sujay Raghavendra Naganna; Sindhu Sreeranga

doi:10.1007/978-981-95-1442-7_7

A Comparative Study on Air Quality Index Prediction Using Machine Learning and Hybrid Deep Learning Models

Nemarugommula Pranav
, Vishal Ganapathy
, B. Geedhavarshini
, Kashmira Nigade
, S. Shreya
, Jagalingam Pushparaj^*
, Sujay Raghavendra Naganna
, Sindhu Sreeranga

^*Corresponding author for this work

Department of Civil Engineering, Manipal Institute of Technology, Bengaluru

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

Abstract

The prediction of the air quality index (AQI) is crucial for public health and environmental protection. In the paper, we used machine learning models like random forest and hybrid deep learning models like bidirectional gated recurrent unit attention mechanism (BiGRU-AM), convolutional neural network-long short-term memory (CNN-LSTM), extreme gradient boosting (XGBoost-CNN-LSTM), and principal component analysis-artificial neural network (PCA-ANN) to predict AQI of various Indian cities. These algorithms were evaluated using coefficient of determination (R²), mean absolute error (MAE), root-mean-squared error (RMSE), and mean absolute percentage error (MAPE) metrics. Our results showed that random forest outperformed the others, followed by BiGRU-AM and CNN-LSTM in terms of predictive accuracy.

Original language	English
Title of host publication	Sustainable Waste Management Practices, Volume 2 - Sustainable Waste Management with Special Focus on Circular Economy
Editors	M. Mansoor Ahammed, Mukesh Khare
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	73-86
Number of pages	14
ISBN (Print)	9789819514410
DOIs	https://doi.org/10.1007/978-981-95-1442-7_7
Publication status	Published - 2025
Event	International Conference on Environmental Science and Technology, ICEST 2024 - Surat, India Duration: 19-12-2024 → 21-12-2024

Publication series

Name	Lecture Notes in Civil Engineering
Volume	732 LNCE
ISSN (Print)	2366-2557
ISSN (Electronic)	2366-2565

Conference

Conference	International Conference on Environmental Science and Technology, ICEST 2024
Country/Territory	India
City	Surat
Period	19-12-24 → 21-12-24

UN SDGs

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

SDG 3 Good Health and Well-being
SDG 11 Sustainable Cities and Communities

All Science Journal Classification (ASJC) codes

Civil and Structural Engineering

Access to Document

10.1007/978-981-95-1442-7_7

Cite this

Pranav, N., Ganapathy, V., Geedhavarshini, B., Nigade, K., Shreya, S., Pushparaj, J., Naganna, S. R., & Sreeranga, S. (2025). A Comparative Study on Air Quality Index Prediction Using Machine Learning and Hybrid Deep Learning Models. In M. M. Ahammed, & M. Khare (Eds.), Sustainable Waste Management Practices, Volume 2 - Sustainable Waste Management with Special Focus on Circular Economy (pp. 73-86). (Lecture Notes in Civil Engineering; Vol. 732 LNCE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-95-1442-7_7

Pranav, Nemarugommula ; Ganapathy, Vishal ; Geedhavarshini, B. et al. / A Comparative Study on Air Quality Index Prediction Using Machine Learning and Hybrid Deep Learning Models. Sustainable Waste Management Practices, Volume 2 - Sustainable Waste Management with Special Focus on Circular Economy. editor / M. Mansoor Ahammed ; Mukesh Khare. Springer Science and Business Media Deutschland GmbH, 2025. pp. 73-86 (Lecture Notes in Civil Engineering).

@inproceedings{c4ba95e4e17e4bdcaff7d6bf6bf10665,

title = "A Comparative Study on Air Quality Index Prediction Using Machine Learning and Hybrid Deep Learning Models",

abstract = "The prediction of the air quality index (AQI) is crucial for public health and environmental protection. In the paper, we used machine learning models like random forest and hybrid deep learning models like bidirectional gated recurrent unit attention mechanism (BiGRU-AM), convolutional neural network-long short-term memory (CNN-LSTM), extreme gradient boosting (XGBoost-CNN-LSTM), and principal component analysis-artificial neural network (PCA-ANN) to predict AQI of various Indian cities. These algorithms were evaluated using coefficient of determination (R2), mean absolute error (MAE), root-mean-squared error (RMSE), and mean absolute percentage error (MAPE) metrics. Our results showed that random forest outperformed the others, followed by BiGRU-AM and CNN-LSTM in terms of predictive accuracy.",

author = "Nemarugommula Pranav and Vishal Ganapathy and B. Geedhavarshini and Kashmira Nigade and S. Shreya and Jagalingam Pushparaj and Naganna, \{Sujay Raghavendra\} and Sindhu Sreeranga",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.; International Conference on Environmental Science and Technology, ICEST 2024 ; Conference date: 19-12-2024 Through 21-12-2024",

year = "2025",

doi = "10.1007/978-981-95-1442-7\_7",

language = "English",

isbn = "9789819514410",

series = "Lecture Notes in Civil Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "73--86",

editor = "Ahammed, \{M. Mansoor\} and Mukesh Khare",

booktitle = "Sustainable Waste Management Practices, Volume 2 - Sustainable Waste Management with Special Focus on Circular Economy",

address = "Germany",

}

Pranav, N, Ganapathy, V, Geedhavarshini, B, Nigade, K, Shreya, S, Pushparaj, J, Naganna, SR & Sreeranga, S 2025, A Comparative Study on Air Quality Index Prediction Using Machine Learning and Hybrid Deep Learning Models. in MM Ahammed & M Khare (eds), Sustainable Waste Management Practices, Volume 2 - Sustainable Waste Management with Special Focus on Circular Economy. Lecture Notes in Civil Engineering, vol. 732 LNCE, Springer Science and Business Media Deutschland GmbH, pp. 73-86, International Conference on Environmental Science and Technology, ICEST 2024, Surat, India, 19-12-24. https://doi.org/10.1007/978-981-95-1442-7_7

A Comparative Study on Air Quality Index Prediction Using Machine Learning and Hybrid Deep Learning Models. / Pranav, Nemarugommula; Ganapathy, Vishal; Geedhavarshini, B. et al.
Sustainable Waste Management Practices, Volume 2 - Sustainable Waste Management with Special Focus on Circular Economy. ed. / M. Mansoor Ahammed; Mukesh Khare. Springer Science and Business Media Deutschland GmbH, 2025. p. 73-86 (Lecture Notes in Civil Engineering; Vol. 732 LNCE).

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

TY - GEN

T1 - A Comparative Study on Air Quality Index Prediction Using Machine Learning and Hybrid Deep Learning Models

AU - Pranav, Nemarugommula

AU - Ganapathy, Vishal

AU - Geedhavarshini, B.

AU - Nigade, Kashmira

AU - Shreya, S.

AU - Pushparaj, Jagalingam

AU - Naganna, Sujay Raghavendra

AU - Sreeranga, Sindhu

PY - 2025

Y1 - 2025

N2 - The prediction of the air quality index (AQI) is crucial for public health and environmental protection. In the paper, we used machine learning models like random forest and hybrid deep learning models like bidirectional gated recurrent unit attention mechanism (BiGRU-AM), convolutional neural network-long short-term memory (CNN-LSTM), extreme gradient boosting (XGBoost-CNN-LSTM), and principal component analysis-artificial neural network (PCA-ANN) to predict AQI of various Indian cities. These algorithms were evaluated using coefficient of determination (R2), mean absolute error (MAE), root-mean-squared error (RMSE), and mean absolute percentage error (MAPE) metrics. Our results showed that random forest outperformed the others, followed by BiGRU-AM and CNN-LSTM in terms of predictive accuracy.

AB - The prediction of the air quality index (AQI) is crucial for public health and environmental protection. In the paper, we used machine learning models like random forest and hybrid deep learning models like bidirectional gated recurrent unit attention mechanism (BiGRU-AM), convolutional neural network-long short-term memory (CNN-LSTM), extreme gradient boosting (XGBoost-CNN-LSTM), and principal component analysis-artificial neural network (PCA-ANN) to predict AQI of various Indian cities. These algorithms were evaluated using coefficient of determination (R2), mean absolute error (MAE), root-mean-squared error (RMSE), and mean absolute percentage error (MAPE) metrics. Our results showed that random forest outperformed the others, followed by BiGRU-AM and CNN-LSTM in terms of predictive accuracy.

UR - https://www.scopus.com/pages/publications/105020852741

UR - https://www.scopus.com/pages/publications/105020852741#tab=citedBy

U2 - 10.1007/978-981-95-1442-7_7

DO - 10.1007/978-981-95-1442-7_7

M3 - Conference contribution

AN - SCOPUS:105020852741

SN - 9789819514410

T3 - Lecture Notes in Civil Engineering

SP - 73

EP - 86

BT - Sustainable Waste Management Practices, Volume 2 - Sustainable Waste Management with Special Focus on Circular Economy

A2 - Ahammed, M. Mansoor

A2 - Khare, Mukesh

PB - Springer Science and Business Media Deutschland GmbH

T2 - International Conference on Environmental Science and Technology, ICEST 2024

Y2 - 19 December 2024 through 21 December 2024

ER -

Pranav N, Ganapathy V, Geedhavarshini B, Nigade K, Shreya S, Pushparaj J et al. A Comparative Study on Air Quality Index Prediction Using Machine Learning and Hybrid Deep Learning Models. In Ahammed MM, Khare M, editors, Sustainable Waste Management Practices, Volume 2 - Sustainable Waste Management with Special Focus on Circular Economy. Springer Science and Business Media Deutschland GmbH. 2025. p. 73-86. (Lecture Notes in Civil Engineering). doi: 10.1007/978-981-95-1442-7_7

A Comparative Study on Air Quality Index Prediction Using Machine Learning and Hybrid Deep Learning Models

Abstract

Publication series

Conference

UN SDGs

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this