Features inspired PM2.5 prediction: a Belfast city case study

Fareena Naz; Muhammad Fahim; Adnan Ahmad Cheema; Nguyen Trung  Viet; Tuan-Vu  Cao; Trung Q. Duong

doi:10.1007/978-3-031-67357-3_15

Features inspired PM2.5 prediction: a Belfast city case study

Fareena Naz, Muhammad Fahim, Adnan Ahmad Cheema, Nguyen Trung Viet, Tuan-Vu Cao, Trung Q. Duong^*

^*Corresponding author for this work

School of Electronics, Electrical Engineering and Computer Science

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

14 Downloads (Pure)

Abstract

Air pollution is one of the key challenges to both human health and our environment, and managing it requires collective systematic efforts to prevent and mitigate future effects. Fundamentally, this required a better understanding of sources that generate pollution and forecasting models to predict current and future air pollution levels. In this work, we investigated features inspired PM2.5 prediction based on a dataset collected in Northern Ireland, UK. We analysed the influence of different features available in the dataset and newly generated with approaches such as Variational Mode Decomposition (VMD) and evaluated single-step forecasting model performance. We found that a single Long Short Term Memory (LSTM) layer model with a small number of cells and integrated features are sufficient to achieve a good forecasting performance. The combination of VMD integrated features enabled the forecasting model to achieve R²score over 85% and achieve a gain of 6% when compared with lag based prediction only.

Original language	English
Title of host publication	10th EAI International Conference on Industrial Networks and Intelligent Systems (INISCOM 2024): proceedings
Publisher	Springer
Pages	204–212
ISBN (Electronic)	9783031673573
ISBN (Print)	9783031673566
DOIs	https://doi.org/10.1007/978-3-031-67357-3_15
Publication status	Published - 31 Jul 2024
Event	10th EAI International Conference on Industrial Networks and Intelligent Systems 2024 - Viet Nam, Da Nang, Viet Nam Duration: 20 Feb 2024 → 21 Feb 2024 https://iniscom.eai-conferences.org/2024/

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
Volume	595
ISSN (Print)	1867-8211
ISSN (Electronic)	1867-822X

Conference

Conference	10th EAI International Conference on Industrial Networks and Intelligent Systems 2024
Abbreviated title	EAI INISCOM 2024
Country/Territory	Viet Nam
City	Da Nang
Period	20/02/2024 → 21/02/2024
Internet address	https://iniscom.eai-conferences.org/2024/

Publications and Copyright Policy

This work is licensed under Queen’s Research Publications and Copyright Policy.

Keywords

feature generation
signal decomposition
PM2.5
machine learning
forecasting models
long short term memory (LSTM)
air pollutant prediction
air quality
health

UN SDGs

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

Access to Document

10.1007/978-3-031-67357-3_15Licence: Unspecified

Features inspired PM2.5 prediction: a Belfast city case study
Copyright 2024 the authors. This is an accepted manuscript distributed under a Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium, provided the author and source are cited.
Accepted author manuscript, 984 KBLicence: CC BY

Cite this

Naz, F., Fahim, M., Cheema, A. A., Viet, N. T., Cao, T.-V., & Duong, T. Q. (2024). Features inspired PM2.5 prediction: a Belfast city case study. In 10th EAI International Conference on Industrial Networks and Intelligent Systems (INISCOM 2024): proceedings (pp. 204–212). (Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering; Vol. 595). Springer. https://doi.org/10.1007/978-3-031-67357-3_15

Naz, Fareena ; Fahim, Muhammad ; Cheema, Adnan Ahmad et al. / Features inspired PM2.5 prediction: a Belfast city case study. 10th EAI International Conference on Industrial Networks and Intelligent Systems (INISCOM 2024): proceedings. Springer, 2024. pp. 204–212 (Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering).

@inproceedings{6ac36448b2934bbeac210a9bcf8bb4cc,

title = "Features inspired PM2.5 prediction: a Belfast city case study",

abstract = "Air pollution is one of the key challenges to both human health and our environment, and managing it requires collective systematic efforts to prevent and mitigate future effects. Fundamentally, this required a better understanding of sources that generate pollution and forecasting models to predict current and future air pollution levels. In this work, we investigated features inspired PM2.5 prediction based on a dataset collected in Northern Ireland, UK. We analysed the influence of different features available in the dataset and newly generated with approaches such as Variational Mode Decomposition (VMD) and evaluated single-step forecasting model performance. We found that a single Long Short Term Memory (LSTM) layer model with a small number of cells and integrated features are sufficient to achieve a good forecasting performance. The combination of VMD integrated features enabled the forecasting model to achieve R2 score over 85% and achieve a gain of 6% when compared with lag based prediction only.",

keywords = "feature generation, signal decomposition, PM2.5, machine learning, forecasting models, long short term memory (LSTM), air pollutant prediction, air quality, health",

author = "Fareena Naz and Muhammad Fahim and Cheema, {Adnan Ahmad} and Viet, {Nguyen Trung} and Tuan-Vu Cao and Duong, {Trung Q.}",

year = "2024",

month = jul,

day = "31",

doi = "10.1007/978-3-031-67357-3_15",

language = "English",

isbn = "9783031673566",

series = "Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering",

publisher = "Springer",

pages = "204–212",

booktitle = "10th EAI International Conference on Industrial Networks and Intelligent Systems (INISCOM 2024): proceedings",

note = "10th EAI International Conference on Industrial Networks and Intelligent Systems 2024, EAI INISCOM 2024 ; Conference date: 20-02-2024 Through 21-02-2024",

url = "https://iniscom.eai-conferences.org/2024/",

}

Naz, F , Fahim, M, Cheema, AA, Viet, NT, Cao, T-V & Duong, TQ 2024, Features inspired PM2.5 prediction: a Belfast city case study. in 10th EAI International Conference on Industrial Networks and Intelligent Systems (INISCOM 2024): proceedings. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol. 595, Springer, pp. 204–212, 10th EAI International Conference on Industrial Networks and Intelligent Systems 2024, Da Nang, Viet Nam, 20/02/2024. https://doi.org/10.1007/978-3-031-67357-3_15

Features inspired PM2.5 prediction: a Belfast city case study. / Naz, Fareena ; Fahim, Muhammad; Cheema, Adnan Ahmad et al.
10th EAI International Conference on Industrial Networks and Intelligent Systems (INISCOM 2024): proceedings. Springer, 2024. p. 204–212 (Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering; Vol. 595).

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

TY - GEN

T1 - Features inspired PM2.5 prediction: a Belfast city case study

AU - Naz, Fareena

AU - Fahim, Muhammad

AU - Cheema, Adnan Ahmad

AU - Viet, Nguyen Trung

AU - Cao, Tuan-Vu

AU - Duong, Trung Q.

PY - 2024/7/31

Y1 - 2024/7/31

N2 - Air pollution is one of the key challenges to both human health and our environment, and managing it requires collective systematic efforts to prevent and mitigate future effects. Fundamentally, this required a better understanding of sources that generate pollution and forecasting models to predict current and future air pollution levels. In this work, we investigated features inspired PM2.5 prediction based on a dataset collected in Northern Ireland, UK. We analysed the influence of different features available in the dataset and newly generated with approaches such as Variational Mode Decomposition (VMD) and evaluated single-step forecasting model performance. We found that a single Long Short Term Memory (LSTM) layer model with a small number of cells and integrated features are sufficient to achieve a good forecasting performance. The combination of VMD integrated features enabled the forecasting model to achieve R2 score over 85% and achieve a gain of 6% when compared with lag based prediction only.

AB - Air pollution is one of the key challenges to both human health and our environment, and managing it requires collective systematic efforts to prevent and mitigate future effects. Fundamentally, this required a better understanding of sources that generate pollution and forecasting models to predict current and future air pollution levels. In this work, we investigated features inspired PM2.5 prediction based on a dataset collected in Northern Ireland, UK. We analysed the influence of different features available in the dataset and newly generated with approaches such as Variational Mode Decomposition (VMD) and evaluated single-step forecasting model performance. We found that a single Long Short Term Memory (LSTM) layer model with a small number of cells and integrated features are sufficient to achieve a good forecasting performance. The combination of VMD integrated features enabled the forecasting model to achieve R2 score over 85% and achieve a gain of 6% when compared with lag based prediction only.

KW - feature generation

KW - signal decomposition

KW - PM2.5

KW - machine learning

KW - forecasting models

KW - long short term memory (LSTM)

KW - air pollutant prediction

KW - air quality

KW - health

U2 - 10.1007/978-3-031-67357-3_15

DO - 10.1007/978-3-031-67357-3_15

M3 - Conference contribution

SN - 9783031673566

T3 - Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

SP - 204

EP - 212

BT - 10th EAI International Conference on Industrial Networks and Intelligent Systems (INISCOM 2024): proceedings

PB - Springer

T2 - 10th EAI International Conference on Industrial Networks and Intelligent Systems 2024

Y2 - 20 February 2024 through 21 February 2024

ER -

Naz F , Fahim M, Cheema AA, Viet NT, Cao TV, Duong TQ. Features inspired PM2.5 prediction: a Belfast city case study. In 10th EAI International Conference on Industrial Networks and Intelligent Systems (INISCOM 2024): proceedings. Springer. 2024. p. 204–212. (Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering). doi: 10.1007/978-3-031-67357-3_15

Features inspired PM2.5 prediction: a Belfast city case study

Abstract

Publication series

Conference

Publications and Copyright Policy

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this