Open Access: A stochastic locally diffusive model with neural network-based deformations for global sea surface temperature

Every week, we select a recently published Open Access article to feature. This week’s article is from Stat and proposes a new approach to modelling spatio-temporal global data. 

The article’s abstract is given below, with the full article available to read here.

Hu, W.Fuglstad, G.-A., & Castruccio, S. (2022). A stochastic locally diffusive model with neural network-based deformations for global sea surface temperatureStat111), e431. https://doi.org/10.1002/sta4.431
 
In this work, we propose a new approach to model large, irregularly distributed spatio-temporal global data via a locally diffusive stochastic partial differential equation (SPDE). The proposed model assumes a local deformation of the SPDE with non-linear dependence on the covariates through a neural network. The proposed model can be fit in a computationally efficient manner using a triangulation over the sphere and sparsity of the precision matrix, as shown in an application with a large data set of simulated multi-decadal monthly sea surface temperature.
 
More Details