RT journal article
T1 Air Pollution PM10 Forecasting Maps in the Maritime Area of the Bay of Algeciras (Spain)
A1 Rodríguez García, María Inmaculada
A1 Carrasco García, María Gema
A1 Rodrigues Ribeiro, Maria da Conceição
A1 González Enrique, Francisco  Javier
A1 Ruiz Águilar, Juan Jesús
A1 Turias Domínguez, Ignacio José
A2 Ingeniería Industrial e Ingeniería Civil
A2 Ingeniería Informática
K1 air pollution forecasting
K1 data fusion
K1 image processing
K1 pattern recognition
AB Predicting the levels of a pollutant in a given area is an open problem, mainly becausehistorical data are typically available at certain locations, where monitoring stations are located, butnot at all locations in the area. This work presents an approach based on developing predictions ateach of the points where an immission station is available; in this case, based on shallow ArtificialNeural Networks, ANNs, and then using a simple geostatistical interpolation algorithm (InverseDistanceWeighted, IDW), a pollutant map is constructed over the entire study area, thus providingpredictions at each point in the plane. The ANN models are designed to make 1 h ahead and 4 hahead predictions, using an autoregressive scheme as inputs (in the case of 4 h ahead as a jumpingstrategy). The results are then compared using the Friedman and Bonferroni tests to select the bestmodel at each location, and predictions are made with all the best models. In general, to the 1 hahead prediction models, the optimal models typically have fewer neurons and require minimalhistorical data. For instance, the best model in Algeciras has an R of almost 0.89 and consists of 1hidden neuron and 3 to 5 lags, similar to Colegio Los Barrios. In the case of 4h ahead prediction,Colegio Carteya station shows the best model, with an R of almost 0.89 and a MSE of less than 240,including 5 hidden neurons and different lags from the past. The results are sufficiently adequate,especially in the case of predictions 4 h into the future. The aim is to integrate the models into a toolfor citizens and administrations to make decisions.
PB MDPI
SN 2077-1312
YR 2024
FD 2024
LK http://hdl.handle.net/10498/33693
UL http://hdl.handle.net/10498/33693
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 21-sep-2026