In this article, we provide a comprehensive review of space–time covariance functions. As
for the spatial domain, we focus on either the d‐dimensional Euclidean space or on the unit …

In recent years, interest has grown in modeling spatio-temporal data generated from
monitoring networks, satellite imaging, and climate models. Under Gaussianity, the …

Gaussian processes and random fields have a long history, covering multiple approaches to
representing spatial and spatio-temporal dependence structures, such as covariance …

We described the key features of the pragmatic geostatistical methodology aiming at
resolving the following drawbacks of classical geostatistical models: assuming that the data …

Gaussian processes are an effective model class for learning unknown functions,
particularly in settings where accurately representing predictive uncertainty is of key …

Active source seismology provides a critical constraint on the global crustal structure.
However, the heterogeneous data coverage means that interpolation is necessary to fill the …

The Matern Model: A Journey Through Statistics, Numerical Analysis and Machine Learning
Page 1 Statistical Science 2024, Vol. 39, No. 3, 469–492 https://doi.org/10.1214/24-STS923 © …

Vecchia's approximate likelihood for Gaussian process parameters depends on how the
observations are ordered, which has been cited as a deficiency. This article takes the …

The last decades have seen an unprecedented increase in the availability of data sets that
are inherently global and temporally evolving, from remotely sensed networks to climate …

Gaussian processes are arguably the most important class of spatiotemporal models within
machine learning. They encode prior information about the modeled function and can be …