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

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.

Cite

Text

De Felice et al. "Spatio-Temporal Weathering Predictions in the Sparse Data Regime with Gaussian Processes." NeurIPS 2022 Workshops: AI4Science, 2022.

Markdown

[De Felice et al. "Spatio-Temporal Weathering Predictions in the Sparse Data Regime with Gaussian Processes." NeurIPS 2022 Workshops: AI4Science, 2022.](https://mlanthology.org/neuripsw/2022/felice2022neuripsw-spatiotemporal/)

BibTeX

@inproceedings{felice2022neuripsw-spatiotemporal,
  title     = {{Spatio-Temporal Weathering Predictions in the Sparse Data Regime with Gaussian Processes}},
  author    = {De Felice, Giovanni and Gusev, Vladimir and Goulermas, John Y and Gaultois, Michael and Rosseinsky, Matthew and Gauvin, Catherine Vincent},
  booktitle = {NeurIPS 2022 Workshops: AI4Science},
  year      = {2022},
  url       = {https://mlanthology.org/neuripsw/2022/felice2022neuripsw-spatiotemporal/}
}