Publication:
Hybrid deep learning model for ozone concentration prediction: comprehensive evaluation and comparison with various machine and deep learning algorithms

Simple item page
dc.citedby20
dc.contributor.authorYafouz A.en_US
dc.contributor.authorAhmed A.N.en_US
dc.contributor.authorZaini N.en_US
dc.contributor.authorSherif M.en_US
dc.contributor.authorSefelnasr A.en_US
dc.contributor.authorEl-Shafie A.en_US
dc.contributor.authorid57221981418en_US
dc.contributor.authorid57214837520en_US
dc.contributor.authorid56905328500en_US
dc.contributor.authorid7005414714en_US
dc.contributor.authorid6505592467en_US
dc.contributor.authorid16068189400en_US
dc.date.accessioned2023-05-29T09:11:41Z
dc.date.available2023-05-29T09:11:41Z
dc.date.issued2021
dc.description.abstractTo accurately predict tropospheric ozone concentration(O3), it is needed to investigate the variety of artificial intelligence techniques� performance, such as machine learning, deep learning and hybrid models. This research aims to effectively predict the hourly ozone trend via fewer input variables. This ozone prediction attempt is performed on diversity data of air pollutants (NO2, NOx, CO, SO2) and meteorological parameters (wind-speed and humidity). The historical datasets are collected from 3 sites in Malaysia. The study�s methodology progressed in two paths: standalone and hybrid models where hourly-averaged datasets are applied based on 5-time horizon analysis scenario, with different inputs� combinations. For evaluation, all models are tested throughout 5-performance indicator and illustrated on Modified Taylor diagram. Sensitivity analysis of input variables is quantified. Additionally, uncertainty analysis is conducted to assess their confidence level associated with Willmott Index. Based on R 2, results indicated that XGBoost has higher accuracy compared to MLP and SVR; meanwhile, LSTM and CNN outweighs XGBoost. In terms of robustness and accuracy, the proposed hybrid model possesses superlative performance compared to all above-mentioned techniques. The proposed model achieved exceptional results as the highest R 2, the highest 95% confidence degree, and narrower confidence interval width, are 93.48%, 98.16%, and 0.0014195, respectively. � 2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.en_US
dc.description.natureFinalen_US
dc.identifier.doi10.1080/19942060.2021.1926328
dc.identifier.epage933
dc.identifier.issue1
dc.identifier.scopus2-s2.0-85106308124
dc.identifier.spage902
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85106308124&doi=10.1080%2f19942060.2021.1926328&partnerID=40&md5=4524da5088f50ee5d7d3ac871a2279a2
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/26537
dc.identifier.volume15
dc.publisherTaylor and Francis Ltd.en_US
dc.relation.ispartofAll Open Access, Gold
dc.sourceScopus
dc.sourcetitleEngineering Applications of Computational Fluid Mechanics
dc.titleHybrid deep learning model for ozone concentration prediction: comprehensive evaluation and comparison with various machine and deep learning algorithmsen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS