2026-06-02T06:37:16Zhttps://riubu.ubu.es/oai/request

oai:riubu.ubu.es:10259/72332023-02-16T12:37:58Zcom_10259_3847com_10259_5086com_10259_2604col_10259_3848

González Enrique, Francisco Javier Ruiz Aguilar, Juan Jesús Moscoso López, José Antonio Urda Muñoz, Daniel Deka, Lipika Turias Domínguez, Ignacio J. Forecasting Feature selection Air pollution Nitrogen dioxide Artificial neural networks LSTMs Exogenous variables Deep learning Time series This 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. 2023-01-12 2023-01-12 2021-03 info:eu-repo/semantics/article http://hdl.handle.net/10259/7233 10.3390/s21051770 1424-8220 eng Sensors. 2021, V. 21, n. 5, 1770 https://doi.org/10.3390/s21051770 info: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 FORECASTING http://creativecommons.org/licenses/by/4.0/ info:eu-repo/semantics/openAccess Atribución 4.0 Internacional MDPI