Air Quality Prediction Using Cnn Plus Lstm-Based Hybrid Deep Learning Architecture

dc.authoridOgrenci, Arif Selcuk/0000-0003-0463-3019
dc.authoridGILIK, AYSENUR/0000-0003-3297-5964
dc.authorwosidOgrenci, Arif Selcuk/W-1372-2017
dc.contributor.authorGilik, Aysenur
dc.contributor.authorOgrenci, Arif Selcuk
dc.contributor.authorOzmen, Atilla
dc.date.accessioned2023-10-19T15:12:45Z
dc.date.available2023-10-19T15:12:45Z
dc.date.issued2022
dc.department-temp[Gilik, Aysenur; Ogrenci, Arif Selcuk; Ozmen, Atilla] Kadir Has Univ, Elect & Elect Engn Dept, Istanbul, Turkeyen_US
dc.description.abstractAir pollution prediction based on variables in environmental monitoring data gains further importance with increasing concerns about climate change and the sustainability of cities. Modeling of the complex relationships between these variables by sophisticated methods in machine learning is a promising field. The objectives of this work are to develop a supervised model for the prediction of air pollution by using real sensor data and to transfer the model between cities. The combination of a convolutional neural network and a long short-term memory deep neural network model was proposed to predict the concentration of air pollutants in multiple locations of a city by using spatial-temporal relationships. Two approaches have been adopted: the univariate model contains the information of one pollutant whereas the multivariate model contains the information of all pollutants and meteorology data for prediction. The study was carried out for different pollutants which are in the publicly available data of the cities of Barcelona, Kocaeli, and Istanbul. The hyperparameters of the model (filter, frame, and batch sizes; number of convolutional/LSTM layers and hidden units; learning rate; and parameters for sample selection, pooling, and validation) were tuned to determine the architecture that achieved the lowest test error. The proposed model improved the prediction performance (measured by the root mean square error) by 11-53% for particulate matter, 20-31% for ozone, 9-47% for nitrogenoxides, and 18-46% for sulfurdioxide with respect to the 1-hidden layer long short-term memory networks utilized in the literature. The multivariate model without using meteorological data revealed the best results. Regarding transfer learning, the network weights were transferred from the source city to the target city. The model has more accurate prediction performance with the transfer of the network from Kocaeli to Istanbul as those neighbor cities have similar air pollution and meteorological characteristics.en_US
dc.identifier.citation40
dc.identifier.doi10.1007/s11356-021-16227-wen_US
dc.identifier.endpage11938en_US
dc.identifier.issn0944-1344
dc.identifier.issn1614-7499
dc.identifier.issue8en_US
dc.identifier.pmid34554404en_US
dc.identifier.scopus2-s2.0-85115382102en_US
dc.identifier.scopusqualityQ1
dc.identifier.startpage11920en_US
dc.identifier.urihttps://doi.org/10.1007/s11356-021-16227-w
dc.identifier.urihttps://hdl.handle.net/20.500.12469/5523
dc.identifier.volume29en_US
dc.identifier.wosWOS:000698576900009en_US
dc.identifier.wosqualityQ2
dc.institutionauthorÖzmen, Atilla
dc.khas20231019-WoSen_US
dc.language.isoenen_US
dc.publisherSpringer Heidelbergen_US
dc.relation.ispartofEnvironmental Science and Pollution Researchen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectDeep learningen_US
dc.subjectAir pollutionen_US
dc.subjectPredictionen_US
dc.subjectConvolutional neural networken_US
dc.subjectLong short-term memoryen_US
dc.subjectTransfer learningen_US
dc.titleAir Quality Prediction Using Cnn Plus Lstm-Based Hybrid Deep Learning Architectureen_US
dc.typeArticleen_US
dspace.entity.typePublication
relation.isAuthorOfPublicationcf8f9e05-3f89-4ab6-af78-d0937210fb77
relation.isAuthorOfPublication.latestForDiscoverycf8f9e05-3f89-4ab6-af78-d0937210fb77

Files