Publications

Spatio-Temporal Weathering Predictions in the Sparse Data Regime with Gaussian Processes

Giovanni De Felice, Vladimir Gusev, John Goulermas, Michael Gaultois, Matthew Rosseinsky, Catherine Vincent Gauvin

Tags: spatio-temporal
Venue: AI4Science NeurIPS 2022

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.

google scholar old readthedocs.io icon Google Scholar night mode building arrow up arrow left view minus share gmlg arrow right placeholder paper plane newspaper mail heart link menu broken link dots like plus arrow down graph academic cap world sensor network interpolation usi blackboard youtube twitter instagram linkedin github facebook skype