A Data Fusion Model for Meteorological Data using the INLA-SPDE method

Abstract

This work aims to combine two primary meteorological data sources in the Philippines: data from a sparse network of weather stations and outcomes of a numerical weather prediction model. To this end, we propose a data fusion model which is primarily motivated by the problem of sparsity in the observational data and the use of a numerical prediction model as an additional data source in order to obtain better predictions for the variables of interest. The proposed data fusion model assumes that the different data sources are error-prone realizations of a common latent process. The outcomes from the weather stations follow the classical error model while the outcomes of the numerical weather prediction model involves a constant multiplicative bias parameter and an additive bias which is spatially-structured and time-varying. We use a Bayesian model averaging approach with the integrated nested Laplace approximation (INLA) for doing inference. The proposed data fusion model outperforms the stations-only model and the regression calibration approach, when assessed using leave-group-out cross-validation (LGOCV). We assess the benefits of data fusion and evaluate the accuracy of predictions and parameter estimation through a simulation study. The results show that the proposed data fusion model generally gives better predictions compared to the stations-only approach especially with sparse observational data.