Spatial prediction of air pollution levels using a hierarchical Bayesian spatiotemporal model in Catalonia, Spain. (May 2022)

• Record Type: Journal Article
• Authors: Saez, Marc; Barceló, Maria A.
• Is Part Of: Environmental modelling & software. Volume 151(2022)
• Publication Date: 2022-05
• Subjects: Spatial predictions -- Hierarchical Bayesian spatiotemporal model -- Stochastic partial differential equations (SPDE) -- Integrated nested laplace approximations (INLA); Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2022.105369
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: Our objective in this work was to present a hierarchical Bayesian spatiotemporal model that allowed us to make spatial predictions of air pollution levels effectively and with very few computational costs. We specified a hierarchical spatiotemporal model using the Stochastic Partial Differential Equations of the integrated nested Laplace approximations approximation. This approach allowed us to spatially predict in the territory of Catalonia (Spain) the levels of the four pollutants for which there is the most evidence of an adverse health effect. Our model allowed us to make fairly accurate spatial predictions of both long-term and short-term exposure to air pollutants with a relatively low density of monitoring stations and at a much lower computation time. The only requirements of our method are the minimum number of stations distributed throughout the territory where the predictions are to be made, and that the spatial and temporal dimensions are either independent or separable. Graphical abstract: Image 1 Highlights: We show a hierarchical Bayesian spatiotemporal model. Our model provides predictions of both long-term and short-term exposure. The computational cost is low. The model only needs a minimum number of stations being distributed throughout the territory. The other requirement of our model is that the spatial and temporal dimensions are either independent or separable.