Keywords: materials weathering, gaussian processes, spatio-temporal kriging, contextual features, sparse data
TL;DR: We propose a Spatio-Temporal Gaussian Process for weathering predictions from sparse observations.
Abstract: We investigate the problem of predicting the expected lifetime of a material in different climatic conditions from a few observations in sparsely located testing facilities. We propose a Spatio-Temporal adaptation of Gaussian Process Regression that takes full advantage of high-quality satellite data by performing an interpolation directly in the space of climatological time-series. We illustrate our approach by predicting gloss retention of industrial paint formulations. Furthermore, our model provides uncertainty that can guide decision-making and is applicable to a wide range of problems.