English

BlackBox: Generalizable Reconstruction of Extremal Values from Incomplete Spatio-Temporal Data

Machine Learning 2020-10-09 v3 Machine Learning

Abstract

We describe our submission to the Extreme Value Analysis 2019 Data Challenge in which teams were asked to predict extremes of sea surface temperature anomaly within spatio-temporal regions of missing data. We present a computational framework which reconstructs missing data using convolutional deep neural networks. Conditioned on incomplete data, we employ autoencoder-like models as multivariate conditional distributions from which possible reconstructions of the complete dataset are sampled using imputed noise. In order to mitigate bias introduced by any one particular model, a prediction ensemble is constructed to create the final distribution of extremal values. Our method does not rely on expert knowledge in order to accurately reproduce dynamic features of a complex oceanographic system with minimal assumptions. The obtained results promise reusability and generalization to other domains.

Keywords

Cite

@article{arxiv.2005.02140,
  title  = {BlackBox: Generalizable Reconstruction of Extremal Values from Incomplete Spatio-Temporal Data},
  author = {Tomislav Ivek and Domagoj Vlah},
  journal= {arXiv preprint arXiv:2005.02140},
  year   = {2020}
}

Comments

3 figures; accepted in Extremes; 2nd place entry at the Extreme Value Analysis 2019 Data Challenge

R2 v1 2026-06-23T15:19:16.597Z