Hybrid artificial neural network models for effective prediction and mitigation of urban roadside NO2 pollution

Research output: Contribution to journalConference article

6 Citations (Scopus)

Abstract

Traffic-related air pollution has been a serious concern amongst policy-makers and the public due to its physiological and environmental impacts. An early warning system based on accurate forecasting tools must therefore be implemented to circumvent the adverse effects of exposure to major air pollutants. A multilayer perceptron neural network was trained and developed using air pollution and meteorological data over a two-year period from a monitoring site in Marylebone Road, Central London to predict roadside concentration values of NO2 24 hours ahead. Several hybrid models were also developed by applying feature selection techniques such as stepwise regression, principal component analysis, and Classification and Regression Trees to the neural network model. Most roadside pollutant variables, e.g., oxides of nitrogen, were found to be significant in predicting NO2. The statistical results reveal overall prediction superiority of the hybrid models to the standalone neural network model.

LanguageEnglish
Pages3524-3530
Number of pages7
JournalEnergy Procedia
Volume142
DOIs
Publication statusPublished - 31 Dec 2017
Event9th International Conference on Applied Energy, ICAE 2017 - Cardiff, United Kingdom
Duration: 21 Aug 201724 Aug 2017

Fingerprint

Roadsides
Pollution
Neural networks
Air pollution
Alarm systems
Multilayer neural networks
Principal component analysis
Environmental impact
Feature extraction
Nitrogen
Oxides
Monitoring
Air

Keywords

  • air pollution forecasting
  • artificial intelligence
  • artificial neural network
  • multilayer perceptron
  • NO

Cite this

@article{00a3b49d25ca40c5b27df9bf43f9e9fe,
title = "Hybrid artificial neural network models for effective prediction and mitigation of urban roadside NO2 pollution",
abstract = "Traffic-related air pollution has been a serious concern amongst policy-makers and the public due to its physiological and environmental impacts. An early warning system based on accurate forecasting tools must therefore be implemented to circumvent the adverse effects of exposure to major air pollutants. A multilayer perceptron neural network was trained and developed using air pollution and meteorological data over a two-year period from a monitoring site in Marylebone Road, Central London to predict roadside concentration values of NO2 24 hours ahead. Several hybrid models were also developed by applying feature selection techniques such as stepwise regression, principal component analysis, and Classification and Regression Trees to the neural network model. Most roadside pollutant variables, e.g., oxides of nitrogen, were found to be significant in predicting NO2. The statistical results reveal overall prediction superiority of the hybrid models to the standalone neural network model.",
keywords = "air pollution forecasting, artificial intelligence, artificial neural network, multilayer perceptron, NO",
author = "Cabaneros, {Sheen Mclean S.} and Calautit, {John Kaiser S.} and Hughes, {Ben Richard}",
year = "2017",
month = "12",
day = "31",
doi = "10.1016/j.egypro.2017.12.240",
language = "English",
volume = "142",
pages = "3524--3530",
journal = "Energy Procedia",
issn = "1876-6102",

}

Hybrid artificial neural network models for effective prediction and mitigation of urban roadside NO2 pollution. / Cabaneros, Sheen Mclean S.; Calautit, John Kaiser S.; Hughes, Ben Richard.

In: Energy Procedia, Vol. 142, 31.12.2017, p. 3524-3530.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Hybrid artificial neural network models for effective prediction and mitigation of urban roadside NO2 pollution

AU - Cabaneros, Sheen Mclean S.

AU - Calautit, John Kaiser S.

AU - Hughes, Ben Richard

PY - 2017/12/31

Y1 - 2017/12/31

N2 - Traffic-related air pollution has been a serious concern amongst policy-makers and the public due to its physiological and environmental impacts. An early warning system based on accurate forecasting tools must therefore be implemented to circumvent the adverse effects of exposure to major air pollutants. A multilayer perceptron neural network was trained and developed using air pollution and meteorological data over a two-year period from a monitoring site in Marylebone Road, Central London to predict roadside concentration values of NO2 24 hours ahead. Several hybrid models were also developed by applying feature selection techniques such as stepwise regression, principal component analysis, and Classification and Regression Trees to the neural network model. Most roadside pollutant variables, e.g., oxides of nitrogen, were found to be significant in predicting NO2. The statistical results reveal overall prediction superiority of the hybrid models to the standalone neural network model.

AB - Traffic-related air pollution has been a serious concern amongst policy-makers and the public due to its physiological and environmental impacts. An early warning system based on accurate forecasting tools must therefore be implemented to circumvent the adverse effects of exposure to major air pollutants. A multilayer perceptron neural network was trained and developed using air pollution and meteorological data over a two-year period from a monitoring site in Marylebone Road, Central London to predict roadside concentration values of NO2 24 hours ahead. Several hybrid models were also developed by applying feature selection techniques such as stepwise regression, principal component analysis, and Classification and Regression Trees to the neural network model. Most roadside pollutant variables, e.g., oxides of nitrogen, were found to be significant in predicting NO2. The statistical results reveal overall prediction superiority of the hybrid models to the standalone neural network model.

KW - air pollution forecasting

KW - artificial intelligence

KW - artificial neural network

KW - multilayer perceptron

KW - NO

UR - http://www.scopus.com/inward/record.url?scp=85041491911&partnerID=8YFLogxK

UR - https://www.sciencedirect.com/journal/energy-procedia

U2 - 10.1016/j.egypro.2017.12.240

DO - 10.1016/j.egypro.2017.12.240

M3 - Conference article

VL - 142

SP - 3524

EP - 3530

JO - Energy Procedia

T2 - Energy Procedia

JF - Energy Procedia

SN - 1876-6102

ER -