{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T16:39:12Z","timestamp":1758818352128,"version":"3.37.3"},"reference-count":55,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2022,3,4]],"date-time":"2022-03-04T00:00:00Z","timestamp":1646352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100004837","name":"MICINN","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,7,25]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The Air Quality Index (AQI) shows the state of air pollution in a unique and more understandable way. This work aims to forecast the AQI in Algeciras (Spain) 8\u00a0hours in advance. The AQI is calculated indirectly through the predicted concentrations of five pollutants (O3, NO2, CO, SO2 and PM10) to achieve this goal. Artificial neural networks (ANNs), sequence-to-sequence long short-term memory networks (LSTMs) and a newly proposed method combing a rolling window with the latter (LSTMNA) are employed as the forecasting techniques. Besides, two input approaches are evaluated: using only the data from the own time series of the pollutant in the first case or adding exogenous variables in the second one. Several window sizes are employed (24, 28 and 72\u00a0hours) with ANNs and LSTMNAs. Additionally, several feature ranking methods are applied in the exogenous approach to select the most relevant lagged variables to feed the models. Results show how the proposed exogenous approach increases the performance of the prediction models. Besides, the newly proposed method LSTMNA provides the best performances in most of the cases evaluated. Hence, it constitutes an exciting alternative to standard LSTMs and ANNs to predict pollutants concentrations and, consequently, the AQI.<\/jats:p>","DOI":"10.1093\/jigpal\/jzac035","type":"journal-article","created":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T20:15:38Z","timestamp":1645560938000},"page":"722-738","source":"Crossref","is-referenced-by-count":5,"title":["Hourly pollutants forecasting using a deep learning approach to obtain the AQI"],"prefix":"10.1093","volume":"31","author":[{"given":"Jos\u00e9 Antonio","family":"Moscoso-L\u00f3pez","sequence":"first","affiliation":[{"name":"University of Cadiz Intelligent Modelling of Systems Research Group, Polytechnic School of Engineering, (Algeciras), , Av. Ramon Puyol s\/n, 11202 Algeciras, Spain"}]},{"given":"Javier","family":"Gonz\u00e1lez-Enrique","sequence":"additional","affiliation":[{"name":"University of Cadiz Intelligent Modelling of Systems Research Group, Polytechnic School of Engineering, (Algeciras), , Av. Ramon Puyol s\/n, 11202 Algeciras, Spain"}]},{"given":"Daniel","family":"Urda","sequence":"additional","affiliation":[{"name":"Universidad de Burgos Grupo de Inteligencia Computacional Aplicada (GICAP), Departamento de Ingenier\u00eda Inform\u00e1tica, Escuela Polit\u00e9cnica Superior, , Av. Cantabria s\/n, 09006 Burgos, Spain"}]},{"given":"Juan Jes\u00fas","family":"Ruiz-Aguilar","sequence":"additional","affiliation":[{"name":"University of Cadiz Intelligent Modelling of Systems Research Group, Polytechnic School of Engineering, (Algeciras), , Av. Ramon Puyol s\/n, 11202 Algeciras, Spain"}]},{"given":"Ignacio J","family":"Turias","sequence":"additional","affiliation":[{"name":"University of Cadiz Intelligent Modelling of Systems Research Group, Polytechnic School of Engineering, (Algeciras), , Av. Ramon Puyol s\/n, 11202 Algeciras, Spain"}]}],"member":"286","published-online":{"date-parts":[[2022,3,4]]},"reference":[{"article-title":"Air quality in Europe\u20142018 report","year":"2018","author":"E. E. Agency","key":"2023072813243033200_ref1"},{"key":"2023072813243033200_ref2","doi-asserted-by":"crossref","first-page":"101472","DOI":"10.1016\/j.scs.2019.101472","article-title":"Enhancing urban ventilation performance through the development of precinct ventilation zones: A case study based on the Greater Sydney, Australia","volume":"47","author":"He","year":"2019","journal-title":"Sustainable Cities and Society"},{"key":"2023072813243033200_ref3","doi-asserted-by":"crossref","first-page":"101471","DOI":"10.1016\/j.scs.2019.101471","article-title":"An intelligent hybrid model for air pollutant concentrations forecasting: Case of Beijing in China","volume":"47","author":"Liu","year":"2019","journal-title":"Sustainable Cities and Society"},{"key":"2023072813243033200_ref4","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.jclepro.2018.03.293","article-title":"Changes in urban air quality during urbanization in China","volume":"188","author":"Lin","year":"2018","journal-title":"Journal of Cleaner Production"},{"key":"2023072813243033200_ref5","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.atmosenv.2016.11.054","article-title":"Relevance analysis and short-term prediction of PM2.5 concentrations in Beijing based on multi-source data","volume":"150","author":"Ni","year":"2017","journal-title":"Atmospheric Environment"},{"key":"2023072813243033200_ref6","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1007\/s11157-010-9227-2","article-title":"Air quality indices: A review","volume":"10","author":"Plaia","year":"2011","journal-title":"Reviews in Environmental Science and Bio\/Technology"},{"key":"2023072813243033200_ref7","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1016\/j.scitotenv.2016.04.081","article-title":"Geostatistical uncertainty of assessing air quality using high-spatial-resolution lichen data: A health study in the urban area of Sines, Portugal","volume":"562","author":"Ribeiro","year":"2016","journal-title":"Science of the Total Environment"},{"key":"2023072813243033200_ref8","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/j.jclepro.2018.10.243","article-title":"Explore a deep learning multi-output neural network for regional multi-step-ahead air quality forecasts","volume":"209","author":"Zhou","year":"2019","journal-title":"Journal of Cleaner Production"},{"key":"2023072813243033200_ref9","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.atmosenv.2018.04.006","article-title":"Application of uncertainty and sensitivity analysis to the air quality SHERPA modelling tool","volume":"183","author":"Pisoni","year":"2018","journal-title":"Atmospheric Environment"},{"key":"2023072813243033200_ref10","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.uclim.2018.01.004","article-title":"Potentials of meteorological characteristics and synoptic conditions to mitigate urban heat island effects","volume":"24","author":"He","year":"2018","journal-title":"Urban Climate"},{"key":"2023072813243033200_ref11","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.envsoft.2016.08.001","article-title":"Atmospheric dispersion modeling using artificial neural network based cellular automata","volume":"85","author":"Lauret","year":"2016","journal-title":"Environmental Modelling & Software"},{"key":"2023072813243033200_ref12","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1016\/j.jclepro.2018.05.151","article-title":"A review on air emissions assessment: Transportation","volume":"194","author":"Van Fan","year":"2018","journal-title":"Journal of Cleaner Production"},{"key":"2023072813243033200_ref13","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1016\/j.jclepro.2017.09.162","article-title":"Mining sequential patterns of PM2.5 pollution in three zones in China","volume":"170","author":"Yang","year":"2018","journal-title":"Journal of Cleaner Production"},{"key":"2023072813243033200_ref14","doi-asserted-by":"crossref","first-page":"1232","DOI":"10.1016\/j.envpol.2017.08.069","article-title":"Daily air quality index forecasting with hybrid models: A case in China","volume":"231","author":"Zhu","year":"2017","journal-title":"Environmental Pollution"},{"key":"2023072813243033200_ref15","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/0957-1272(93)90007-S","article-title":"A neural network-based method for short-term predictions of ambient SO2 concentrations in highly polluted industrial areas of complex terrain","volume":"27","author":"Boznar","year":"1993","journal-title":"Atmospheric Environment. Part B, Urban Atmosphere"},{"key":"2023072813243033200_ref16","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1016\/S1352-2310(98)00230-1","article-title":"Neural network modelling and prediction of hourly NOx and NO2 concentrations in urban air in London","author":"Gardner","year":"1999","journal-title":"Atmospheric Environment"},{"key":"2023072813243033200_ref17","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1080\/10473289.1997.10463925","article-title":"Comparing neural networks and regression models for ozone forecasting","volume":"47","author":"Comrie","year":"1997","journal-title":"Journal of the Air & Waste Management Association"},{"key":"2023072813243033200_ref18","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/S1352-2310(99)00359-3","article-title":"Statistical surface ozone models: An improved methodology to account for non-linear behaviour","volume":"34","author":"Gardner","year":"2000","journal-title":"Atmospheric Environment"},{"key":"2023072813243033200_ref19","doi-asserted-by":"crossref","first-page":"4929","DOI":"10.1016\/S1352-2310(01)00268-0","article-title":"Prediction of sulfur dioxide concentrations at a site near downtown Santiago, Chile","volume":"35","author":"Perez","year":"2001","journal-title":"Atmospheric Environment"},{"key":"2023072813243033200_ref20","doi-asserted-by":"crossref","first-page":"7055","DOI":"10.1016\/j.atmosenv.2003.10.066","article-title":"Progress in developing an ANN model for air pollution index forecast","volume":"38","author":"Jiang","year":"2004","journal-title":"Atmospheric Environment"},{"key":"2023072813243033200_ref21","doi-asserted-by":"crossref","first-page":"3279","DOI":"10.1016\/j.atmosenv.2005.01.050","article-title":"A neural network forecast for daily average PM10 concentrations in Belgium","volume":"39","author":"Hooyberghs","year":"2005","journal-title":"Atmospheric Environment"},{"key":"2023072813243033200_ref22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4236\/jep.2013.412A1001","article-title":"Feed-forward artificial neural network model for air pollutant index prediction in the southern region of peninsular Malaysia","volume":"4","author":"Azid","year":"2013","journal-title":"Journal of Environmental Protection"},{"key":"2023072813243033200_ref23","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1016\/S1352-2310(00)00385-X","article-title":"Neural networks and periodic components used in air quality forecasting","volume":"35","author":"Kolehmainen","year":"2001","journal-title":"Atmospheric Environment"},{"key":"2023072813243033200_ref24","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/S1364-8152(01)00061-5","article-title":"Prediction of sulphur dioxide concentration using artificial neural networks","volume":"17","author":"Chelani","year":"2002","journal-title":"Environmental Modelling & Software"},{"key":"2023072813243033200_ref25","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1007\/s00477-018-01644-0","article-title":"Spatial and meteorological relevance in NO2 estimations. A case study in the Bay of Algeciras (Spain)","volume":"33","author":"Gonz\u00e1lez-Enrique","year":"2019","journal-title":"Stochastic Environmental Research and Risk Assessment"},{"key":"2023072813243033200_ref26","first-page":"681","article-title":"Estimation of NO2 concentration values in a monitoring sensor network using a fusion approach","volume":"28","author":"Gonz\u00e1lez-Enrique","year":"2019","journal-title":"Fresenius Environmental Bulletin"},{"key":"2023072813243033200_ref27","doi-asserted-by":"crossref","first-page":"22408","DOI":"10.1007\/s11356-016-7812-9","article-title":"Deep learning architecture for air quality predictions","volume":"23","author":"Li","year":"2016","journal-title":"Environmental Science and Pollution Research"},{"key":"2023072813243033200_ref28","first-page":"18","article-title":"Air quality prediction in Visakhapatnam with LSTM based recurrent neural networks","volume":"11","author":"Rao","year":"2019","journal-title":"International Journal of Intelligent Systems and Applications"},{"key":"2023072813243033200_ref29","first-page":"1","article-title":"Development of daily PM10 and PM2.5 prediction system using a deep long short-term memory neural network model","author":"Kim","year":"2019","journal-title":"Atmospheric Chemistry and Physics"},{"key":"2023072813243033200_ref30","doi-asserted-by":"crossref","first-page":"1983","DOI":"10.1109\/BigData.2017.8258144","volume-title":"2017 IEEE International Conference on Big Data (Big Data)","author":"K\u00f6k","year":"2017"},{"key":"2023072813243033200_ref31","doi-asserted-by":"crossref","first-page":"1903","DOI":"10.1002\/qj.49712152807","article-title":"Winds in the strait of Gibraltar","volume":"121","author":"Dorman","year":"1995","journal-title":"Quarterly Journal of the Royal Meteorological Society"},{"key":"2023072813243033200_ref32","doi-asserted-by":"crossref","first-page":"670","DOI":"10.1016\/j.envint.2007.01.010","article-title":"Development of an aggregate air quality index for an urban Mediterranean agglomeration: Relation to potential health effects","volume":"33","author":"Kyrkilis","year":"2007","journal-title":"Environment International"},{"article-title":"Guidelines for the reporting of daily air quality\u2014The air quality index (AQI)","year":"2006","author":"U.S. Environmental Protection Agency","key":"2023072813243033200_ref33"},{"key":"2023072813243033200_ref34","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"2023072813243033200_ref35","doi-asserted-by":"crossref","first-page":"2451","DOI":"10.1162\/089976600300015015","article-title":"Learning to forget: Continual prediction with LSTM","volume":"12","author":"Gers","year":"2000","journal-title":"Neural Computation"},{"key":"2023072813243033200_ref36","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1142\/S0218488598000094","article-title":"The vanishing gradient problem during learning recurrent neural nets and problem solutions","volume":"6","author":"Hochreiter","year":"1998","journal-title":"International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems"},{"key":"2023072813243033200_ref37","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1080\/10962247.2018.1459956","article-title":"Forecasting air quality time series using deep learning","volume":"68","author":"Freeman","year":"2018","journal-title":"Journal of the Air & Waste Management Association"},{"key":"2023072813243033200_ref38","first-page":"802","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems\u2014Volume 1","author":"Shi","year":"2015"},{"key":"2023072813243033200_ref39","doi-asserted-by":"crossref","first-page":"318","DOI":"10.7551\/mitpress\/5236.001.0001","volume-title":"Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Volume 1. Foundations","author":"Rumelhart","year":"1986"},{"key":"2023072813243033200_ref40","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11270-014-2063-1","article-title":"Prediction of the level of air pollution using principal component analysis and artificial neural network techniques: A case study in Malaysia","volume":"225","author":"Azid","year":"2014","journal-title":"Water, Air, and Soil Pollution"},{"key":"2023072813243033200_ref41","first-page":"856","volume-title":"Advances in Computational Intelligence. IWANN 2019. Lecture Notes in Computer Science","author":"Gonz\u00e1lez-Enrique","year":"2019"},{"key":"2023072813243033200_ref42","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1007\/s10661-019-7901-6","article-title":"An artificial neural network ensemble approach to generate air pollution maps","volume":"191","author":"Van Roode","year":"2019","journal-title":"Environmental Monitoring and Assessment"},{"key":"2023072813243033200_ref43","doi-asserted-by":"crossref","first-page":"2369","DOI":"10.1007\/s00521-020-05141-w","article-title":"A permutation entropy-based EMD\u2013ANN forecasting ensemble approach for wind speed prediction","volume":"33","author":"Ruiz-Aguilar","year":"2021","journal-title":"Neural Computing and Applications"},{"key":"2023072813243033200_ref44","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1016\/S0893-6080(05)80056-5","article-title":"A scaled conjugate gradient algorithm for fast supervised learning","volume":"6","author":"M\u00f8ller","year":"1993","journal-title":"Neural Networks"},{"key":"2023072813243033200_ref45","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001","volume-title":"Neural Networks for Pattern Recognition","author":"Bishop","year":"1995"},{"key":"2023072813243033200_ref46","first-page":"352","volume-title":"Proceedings of the 27th Symposium on the Interface of Computing Science and Statistics","author":"Sarle","year":"1995"},{"key":"2023072813243033200_ref47","doi-asserted-by":"crossref","first-page":"2627","DOI":"10.1016\/S1352-2310(97)00447-0","article-title":"Artificial neural networks (the multilayer perceptron)\u2014A review of applications in the atmospheric sciences","volume":"32","author":"Gardner","year":"1998","journal-title":"Atmospheric Environment"},{"key":"2023072813243033200_ref48","doi-asserted-by":"crossref","first-page":"1999","DOI":"10.1007\/s00477-021-01992-4","article-title":"A comparison of ranking filter methods applied to the estimation of NO2 concentrations in the Bay of Algeciras (Spain)","volume":"35","author":"Gonz\u00e1lez-Enrique","year":"2021","journal-title":"Stochastic Environmental Research and Risk Assessment"},{"key":"2023072813243033200_ref49","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1109\/TPAMI.2005.159","article-title":"Feature selection based on mutual information: Criteria of max-dependency, max-relevance, and min-redundancy","volume":"27","author":"Peng","year":"2005","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2023072813243033200_ref50","first-page":"3104","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems\u2014Volume 2","author":"Sutskever","year":"2014"},{"key":"2023072813243033200_ref51","doi-asserted-by":"crossref","first-page":"1770","DOI":"10.3390\/s21051770","article-title":"Artificial 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)","volume":"21","author":"Gonz\u00e1lez-Enrique","year":"2021","journal-title":"Sensors"},{"key":"2023072813243033200_ref52","doi-asserted-by":"crossref","DOI":"10.1007\/b97391","volume-title":"Introduction to Time Series and Forecasting","author":"Brockwell","year":"2002"},{"key":"2023072813243033200_ref53","first-page":"123","volume-title":"15th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2020). Advances in Intelligent Systems and Computing","author":"Moscoso-L\u00f3pez","year":"2021"},{"key":"2023072813243033200_ref54","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1080\/01621459.1937.10503522","article-title":"The use of ranks to avoid the assumption of normality implicit in the analysis of variance","volume":"32","author":"Friedman","year":"1937","journal-title":"Journal of the American Statistical Association"},{"key":"2023072813243033200_ref55","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316672","volume-title":"Multiple Comparison Procedures","author":"Hochberg","year":"1987"}],"container-title":["Logic Journal of the IGPL"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jigpal\/article-pdf\/31\/4\/722\/50979277\/jzac035.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jigpal\/article-pdf\/31\/4\/722\/50979277\/jzac035.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,17]],"date-time":"2023-11-17T22:56:22Z","timestamp":1700261782000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jigpal\/article\/31\/4\/722\/6540537"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,4]]},"references-count":55,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,3,4]]},"published-print":{"date-parts":[[2023,7,25]]}},"URL":"https:\/\/doi.org\/10.1093\/jigpal\/jzac035","relation":{},"ISSN":["1367-0751","1368-9894"],"issn-type":[{"type":"print","value":"1367-0751"},{"type":"electronic","value":"1368-9894"}],"subject":[],"published-other":{"date-parts":[[2023,8]]},"published":{"date-parts":[[2022,3,4]]}}}