Show simple item record

dc.contributor.authorGonzález Enrique, Francisco Javier
dc.contributor.authorRuiz Aguilar, Juan Jesús
dc.contributor.authorMoscoso López, José Antonio
dc.contributor.authorUrda Muñoz, Daniel 
dc.contributor.authorDeka, Lipika
dc.contributor.authorTurias Domínguez, Ignacio J.
dc.date.accessioned2023-01-12T13:16:54Z
dc.date.available2023-01-12T13:16:54Z
dc.date.issued2021-03
dc.identifier.urihttp://hdl.handle.net/10259/7233
dc.description.abstractThis study aims to produce accurate predictions of the NO2 concentrations at a specific station of a monitoring network located in the Bay of Algeciras (Spain). Artificial neural networks (ANNs) and sequence-to-sequence long short-term memory networks (LSTMs) were used to create the forecasting models. Additionally, a new prediction method was proposed combining LSTMs using a rolling window scheme with a cross-validation procedure for time series (LSTM-CVT). Two different strategies were followed regarding the input variables: using NO2 from the station or employing NO2 and other pollutants data from any station of the network plus meteorological variables. The ANN and LSTM-CVT exogenous models used lagged datasets of different window sizes. Several feature ranking methods were used to select the top lagged variables and include them in the final exogenous datasets. Prediction horizons of t + 1, t + 4 and t + 8 were employed. The exogenous variables inclusion enhanced the model’s performance, especially for t + 4 (ρ ≈ 0.68 to ρ ≈ 0.74) and t + 8 (ρ ≈ 0.59 to ρ ≈ 0.66). The proposed LSTM-CVT method delivered promising results as the best performing models per prediction horizon employed this new methodology. Additionally, per each parameter combination, it obtained lower error values than ANNs in 85% of the cases.en
dc.description.sponsorshipThis research was funded by MICINN (Ministerio de Ciencia e Innovación-Spain), grant number RTI2018-098160-B-I00, and grant “Ayuda para Estancias en Centros de Investigación del Programa de Fomento e Impulso de la actividad Investigadora de la Universidad de Cádiz”.en
dc.format.mimetypeapplication/pdf
dc.language.isoenges
dc.publisherMDPIes
dc.relation.ispartofSensors. 2021, V. 21, n. 5, 1770es
dc.rightsAtribución 4.0 Internacional*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectForecastingen
dc.subjectFeature selectionen
dc.subjectAir pollutionen
dc.subjectNitrogen dioxideen
dc.subjectArtificial neural networksen
dc.subjectLSTMsen
dc.subjectExogenous variablesen
dc.subjectDeep learningen
dc.subjectTime seriesen
dc.subject.otherInformáticaes
dc.subject.otherComputer scienceen
dc.titleArtificial Neural Networks, Sequence-to-Sequence LSTMs, and Exogenous Variables as Analytical Tools for NO2 (Air Pollution) Forecasting: A Case Study in the Bay of Algeciras (Spain)en
dc.typeinfo:eu-repo/semantics/articlees
dc.rights.accessRightsinfo:eu-repo/semantics/openAccesses
dc.relation.publisherversionhttps://doi.org/10.3390/s21051770es
dc.identifier.doi10.3390/s21051770
dc.relation.projectIDinfo:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/RTI2018-098160-B-I00/ES/DEEP LEARNING IN AIR POLLUTION FORECASTINGen
dc.identifier.essn1424-8220
dc.journal.titleSensorsen
dc.volume.number21es
dc.issue.number5es
dc.type.hasVersioninfo:eu-repo/semantics/publishedVersiones


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record