Dempster-Shafer ensemble learning framework for air pollution nowcasting

Le, TH; Nguyen, HAD; Ha, QP; Tran, MQ; Ahmed, M; Kong, J; Barthelemy, X; Duc, H; Jiang, N; Azzi, M; Riley, M

Dempster-Shafer ensemble learning framework for air pollution nowcasting

Le, TH Nguyen, HAD Ha, QP Tran, MQ Ahmed, M Kong, J Barthelemy, X Duc, H Jiang, N Azzi, M Riley, M

Permalink

Publisher:: EDP Sciences
Publication Type:: Journal Article
Citation:: E3S Web of Conferences, 2025, 626, pp. 01003
Issue Date:: 2025

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Unknown

Download Supporting informationUnknown (63.98 kB)

Adobe PDF

Download Accepted versionAdobe PDF (353 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Le, TH
dc.contributor.author	Nguyen, HAD
dc.contributor.author	Ha, QP
dc.contributor.author	Tran, MQ
dc.contributor.author	Ahmed, M
dc.contributor.author	Kong, J
dc.contributor.author	Barthelemy, X
dc.contributor.author	Duc, H
dc.contributor.author	Jiang, N
dc.contributor.author	Azzi, M
dc.contributor.author	Riley, M
dc.contributor.editor	Truong, N-V
dc.contributor.editor	Ha, QP
dc.date.accessioned	2025-05-06T10:24:29Z
dc.date.available	2025-05-06T10:24:29Z
dc.date.issued	2025
dc.identifier.citation	E3S Web of Conferences, 2025, 626, pp. 01003
dc.identifier.issn	2555-0403
dc.identifier.issn	2267-1242
dc.identifier.uri	http://hdl.handle.net/10453/187211
dc.description.abstract	<jats:p>Deep-learning has emerged as a powerful approach to significantly improve forecast accuracy for air quality estimation. Several models have been developed, demonstrating their own merits in some scenarios and for certain pollutants. In nowcasting, the prediction of air pollution over a small time period essentially demands accurate and reliable estimates, especially in the event cases. From these, selecting the most suitable model to achieve the required forecast performance remains challenging. This paper presents an ensemble framework based on the Dempster-Shafer theory for data fusion to identify the most accurate and reliable forecasts of air pollution obtained from multiple deep neural network models. Our framework is evaluated against three popular machine learning methods, namely, LightGBM, Random Forest, and XGBoost. Experiments are conducted on two horizons: 6-hour and 12-hour predictions using real-world air quality data collected from state-run monitoring stations and low-cost wireless sensor networks.</jats:p>
dc.language	en
dc.publisher	EDP Sciences
dc.relation	NSW Department of Environment and Climate Change
dc.relation.ispartof	E3S Web of Conferences
dc.relation.isbasedon	10.1051/e3sconf/202562601003
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Dempster-Shafer ensemble learning framework for air pollution nowcasting
dc.type	Journal Article
utslib.citation.volume	626
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	University of Technology Sydney/UTS Groups
pubs.organisational-group	University of Technology Sydney/UTS Groups/Centre for Built Infrastructure Resilience (CBIR)
utslib.copyright.status	open_access	*
dc.rights.license	This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/
dc.date.updated	2025-05-06T10:24:26Z
pubs.publication-status	Published
pubs.volume	626

Abstract:

Deep-learning has emerged as a powerful approach to significantly improve forecast accuracy for air quality estimation. Several models have been developed, demonstrating their own merits in some scenarios and for certain pollutants. In nowcasting, the prediction of air pollution over a small time period essentially demands accurate and reliable estimates, especially in the event cases. From these, selecting the most suitable model to achieve the required forecast performance remains challenging. This paper presents an ensemble framework based on the Dempster-Shafer theory for data fusion to identify the most accurate and reliable forecasts of air pollution obtained from multiple deep neural network models. Our framework is evaluated against three popular machine learning methods, namely, LightGBM, Random Forest, and XGBoost. Experiments are conducted on two horizons: 6-hour and 12-hour predictions using real-world air quality data collected from state-run monitoring stations and low-cost wireless sensor networks.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/187211