Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/946
DC FieldValueLanguage
dc.contributor.authorShahriar, S.A.en_US
dc.contributor.authorKayes, I.en_US
dc.contributor.authorHasan, K.en_US
dc.contributor.authorIslam, R.en_US
dc.contributor.authorAwang, N.R.en_US
dc.contributor.authorHamzah, Zen_US
dc.contributor.authorRak, A.E.en_US
dc.contributor.authorSalam, M.A.en_US
dc.date.accessioned2021-03-16T06:06:35Z-
dc.date.available2021-03-16T06:06:35Z-
dc.date.issued2021-
dc.identifier.issn20734433-
dc.identifier.urihttp://hdl.handle.net/123456789/946-
dc.descriptionWeb of Science / Scopusen_US
dc.description.abstractAtmospheric particulate matter (PM) has major threats to global health, especially in urban regions around the world. Dhaka, Narayanganj and Gazipur of Bangladesh are positioned as top ranking polluted metropolitan cities in the world. This study assessed the performance of the application of hybrid models, that is, Autoregressive Integrated Moving Average (ARIMA)-Artificial Neural Network (ANN), ARIMA-Support Vector Machine (SVM) and Principle Component Regression (PCR) along with Decision Tree (DT) and CatBoost deep learning model to predict the ambient PM2.5 concentrations. The data from January 2013 to May 2019 with 2342 observations were utilized in this study. Eighty percent of the data was used as training and the rest of the dataset was employed as testing. The performance of the models was evaluated by R2, RMSE and MAE value. Among the models, CatBoost performed best for predicting PM2.5 for all the stations. The RMSE values during the test period were 12.39 µgm−3, 13.06 µgm−3 and 12.97 µgm−3 for Dhaka, Narayanganj and Gazipur, respectively. Nonetheless, the ARIMA-ANN and DT methods also provided acceptable results. The study suggests adopting deep learning models for predicting atmospheric PM2.5 in Bangladesh.en_US
dc.publisherMDPI AGen_US
dc.relation.ispartofAtmosphereen_US
dc.subjectAir pollutionen_US
dc.subjectARIMA-ANNen_US
dc.subjectARIMA-SVMen_US
dc.subjectCatBoosten_US
dc.subjectDeep learning modelen_US
dc.titlePotential of arima-ann, arima-svm, dt and catboost for atmospheric pm2.5 forecasting in bangladeshen_US
dc.typeNationalen_US
dc.identifier.doi10.3390/atmos12010100-
dc.description.page1-21en_US
dc.volume12(1)en_US
dc.description.articleno100en_US
dc.description.typeArticleen_US
dc.description.impactfactor2.397en_US
dc.description.quartileQ3en_US
item.grantfulltextopen-
item.openairetypeNational-
item.fulltextWith Fulltext-
crisitem.author.deptUniversiti Malaysia Kelantan-
crisitem.author.deptUniversiti Malaysia Kelantan-
crisitem.author.orcidhttps://orcid.org/0000-0003-2093-5113-
Appears in Collections:Faculty of Earth Science - Journal (Scopus/WOS)
Files in This Item:
File Description SizeFormat
atmosphere-12-00100.pdf4.51 MBAdobe PDFView/Open
Show simple item record

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.