Heteroscedastic Gaussian Process Regression on the Alkenone over Sea Surface Temperatures

Taehee Lee; Charles E. Lawrence

doi:10.5065/y82j-f154

Heteroscedastic Gaussian Process Regression on the Alkenone over Sea Surface Temperatures

Applications 2020-01-10 v1 Machine Learning

Authors: Taehee Lee , Charles E. Lawrence

View on arXiv ↗ PDF ↗ DOI ↗

Abstract

To restore the historical sea surface temperatures (SSTs) better, it is important to construct a good calibration model for the associated proxies. In this paper, we introduce a new model for alkenone ( ${\rm{U}}_{37}^{\rm{K}'}$ ) based on the heteroscedastic Gaussian process (GP) regression method. Our nonparametric approach not only deals with the variable pattern of noises over SSTs but also contains a Bayesian method of classifying potential outliers.

Keywords

heteroscedastic gaussian process regression alkenone sea surface temperature calibration model bayesian outlier classification nonparametric approach

Cite

@article{arxiv.1912.08843,
  title  = {Heteroscedastic Gaussian Process Regression on the Alkenone over Sea Surface Temperatures},
  author = {Taehee Lee and Charles E. Lawrence},
  journal= {arXiv preprint arXiv:1912.08843},
  year   = {2020}
}

Comments

This article has been submitted to "Dec 2019, Proceedings of the 9th International Workshop on Climate Informatics: CI 2019. NCAR Technical Note NCAR/TN-561+PROC"

Heteroscedastic Gaussian Process Regression on the Alkenone over Sea Surface Temperatures

Abstract

Keywords

Cite

Comments

Related papers