RT journal article
T1 Long Short-Term Memory Approach for Short-Term Air Quality Forecasting in the Bay of Algeciras (Spain)
A1 Rodríguez García, María Inmaculada
A1 Carrasco García, María Gema
A1 González Enrique, Francisco Javier
A1 Ruíz Aguilar, Juan Jesús
A1 Turias Domínguez, Ignacio José
A2 Ingeniería Industrial e Ingeniería Civil
A2 Ingeniería Informática
K1 air pollution forecasting
K1 LSTM models
K1 deep learning
K1 maritime traffic
K1 ANNs
K1 nitrogen oxides
K1 sulphur dioxide
AB Predicting air quality is a very important task, as it is known to have a significant impact onhealth. The Bay of Algeciras (Spain) is a highly industrialised area with one of the largest superportsin Europe. During the period 2017–2019, different data were recorded in the monitoring stations ofthe bay, forming a database of 131 variables (air pollutants, meteorological information, and vesseldata), which were predicted in the Algeciras station using long short-term memory models. Fourdifferent approaches have been developed to make SO2 and NO2 forecasts 1 h and 4 h in Algeciras.The first uses the remaining 130 exogenous variables. The second uses only the time series datawithout exogenous variables. The third approach consists of using an autoregressive time seriesarrangement as input, and the fourth one is similar, using the time series together with wind and shipdata. The results showed that SO2 is better predicted with autoregressive information and NO2 isbetter predicted with ships and wind autoregressive time series, indicating that NO2 is closely relatedto combustion engines and can be better predicted. The interest of this study is based on the fact thatit can serve as a resource for making informed decisions for authorities, companies, and citizens alike.
PB MDPI
SN 2071-1050
YR 2023
FD 2023
LK http://hdl.handle.net/10498/32478
UL http://hdl.handle.net/10498/32478
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 06-nov-2026