Air Quality Prediction-A Study Using Neural Network Based Approach
Suri, Raunaq Singh ; Jain, Ajay Kumar ; Kapoor, Nishant Raj ; Kumar, Aman ; Arora, Harish Chandra ; Kumar, Krishna LU
and Jahangir, Hashem
(2023)
In Journal of Soft Computing in Civil Engineering
7(1).
p.93-113
- Abstract
India is the 7th largest country by area and 2nd most populated country in the world. The reports prepared by IQAir revels that India is 3rd most polluted country after Bangladesh and Pakistan, on the basis of fine particulates (PM2.5) concentration for the year 2020. In this article, the quality of air in six Indian cities is predicted using data-driven Artificial Neural Network. The data was taken from the 'Kaggle' online source. For six Indian cities, 6139 data sets for ten contaminants (PM2.5, PM10, NO, NO2, NH3, CO, SO2, O3, C6H6 and C7H8) were chosen. The datasets were collected... (More)
India is the 7th largest country by area and 2nd most populated country in the world. The reports prepared by IQAir revels that India is 3rd most polluted country after Bangladesh and Pakistan, on the basis of fine particulates (PM2.5) concentration for the year 2020. In this article, the quality of air in six Indian cities is predicted using data-driven Artificial Neural Network. The data was taken from the 'Kaggle' online source. For six Indian cities, 6139 data sets for ten contaminants (PM2.5, PM10, NO, NO2, NH3, CO, SO2, O3, C6H6 and C7H8) were chosen. The datasets were collected throughout the last five years, from 2016 to 2020, and were used to develop the predictive model. Two machine learning model are proposing in this study namely Artificial Intelligence (AI) and Gaussian Process Regression (GPR) The R-value of ANN and GPR models are 0.9611 and 0.9843 sequentially. The other performance indices such as RMSE, MAPE, MAE of the GPR model are 21.4079, 7.8945% and 13.5884, respectively. The developed model is quite useful to update citizens about the predicted air quality of the urban spaces and protect them from getting affected by the poor ambient air quality. It can also be used to find the proper abatement strategies as well as operational measures.
(Less)
- author
- Suri, Raunaq Singh
; Jain, Ajay Kumar
; Kapoor, Nishant Raj
; Kumar, Aman
; Arora, Harish Chandra
; Kumar, Krishna
LU
and Jahangir, Hashem
- publishing date
- 2023-01
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Air pollution, Air quality prediction, ANN, Artificial intelligence, Smart cities
- in
- Journal of Soft Computing in Civil Engineering
- volume
- 7
- issue
- 1
- pages
- 21 pages
- publisher
- Pouyan Press
- external identifiers
-
- scopus:85145920147
- ISSN
- 2588-2872
- DOI
- 10.22115/SCCE.2022.352017.1488
- language
- English
- LU publication?
- no
- additional info
- Publisher Copyright: © 2022 The Authors. Published by Pouyan Press.
- id
- 461394b1-099e-48f8-ab2e-921c8da0b267
- date added to LUP
- 2024-04-15 13:26:34
- date last changed
- 2024-05-22 09:04:19
@article{461394b1-099e-48f8-ab2e-921c8da0b267,
abstract = {{<p>India is the 7<sup>th</sup> largest country by area and 2<sup>nd</sup> most populated country in the world. The reports prepared by IQAir revels that India is 3<sup>rd</sup> most polluted country after Bangladesh and Pakistan, on the basis of fine particulates (PM<sub>2.5</sub>) concentration for the year 2020. In this article, the quality of air in six Indian cities is predicted using data-driven Artificial Neural Network. The data was taken from the 'Kaggle' online source. For six Indian cities, 6139 data sets for ten contaminants (PM<sub>2.5</sub>, PM<sub>10</sub>, NO, NO<sub>2</sub>, NH<sub>3</sub>, CO, SO<sub>2</sub>, O<sub>3</sub>, C<sub>6</sub>H<sub>6</sub> and C<sub>7</sub>H<sub>8</sub>) were chosen. The datasets were collected throughout the last five years, from 2016 to 2020, and were used to develop the predictive model. Two machine learning model are proposing in this study namely Artificial Intelligence (AI) and Gaussian Process Regression (GPR) The R-value of ANN and GPR models are 0.9611 and 0.9843 sequentially. The other performance indices such as RMSE, MAPE, MAE of the GPR model are 21.4079, 7.8945% and 13.5884, respectively. The developed model is quite useful to update citizens about the predicted air quality of the urban spaces and protect them from getting affected by the poor ambient air quality. It can also be used to find the proper abatement strategies as well as operational measures.</p>}},
author = {{Suri, Raunaq Singh and Jain, Ajay Kumar and Kapoor, Nishant Raj and Kumar, Aman and Arora, Harish Chandra and Kumar, Krishna and Jahangir, Hashem}},
issn = {{2588-2872}},
keywords = {{Air pollution; Air quality prediction; ANN; Artificial intelligence; Smart cities}},
language = {{eng}},
number = {{1}},
pages = {{93--113}},
publisher = {{Pouyan Press}},
series = {{Journal of Soft Computing in Civil Engineering}},
title = {{Air Quality Prediction-A Study Using Neural Network Based Approach}},
url = {{http://dx.doi.org/10.22115/SCCE.2022.352017.1488}},
doi = {{10.22115/SCCE.2022.352017.1488}},
volume = {{7}},
year = {{2023}},
}