Sparse Variational Contaminated Noise Gaussian Process Regression with Applications in Geomagnetic Perturbations Forecasting

TL;DR

This paper introduces a scalable sparse variational Gaussian process regression method with contaminated normal likelihood to improve modeling of heteroscedastic noise and outliers, demonstrated on geomagnetic perturbation forecasting.

Contribution

It extends Gaussian Process regression with a contaminated normal likelihood and develops a scalable inference algorithm for large datasets.

Findings

Shorter prediction intervals with similar coverage and accuracy compared to neural networks.

Effective modeling of heteroscedastic noise and outliers in large datasets.

Improved geomagnetic perturbation forecasts.

Abstract

Gaussian Processes (GP) have become popular machine-learning methods for kernel-based learning on datasets with complicated covariance structures. In this paper, we present a novel extension to the GP framework using a contaminated normal likelihood function to better account for heteroscedastic variance and outlier noise. We propose a scalable inference algorithm based on the Sparse Variational Gaussian Process (SVGP) method for fitting sparse Gaussian process regression models with contaminated normal noise on large datasets. We examine an application to geomagnetic ground perturbations, where the state-of-the-art prediction model is based on neural networks. We show that our approach yields shorter prediction intervals for similar coverage and accuracy when compared to an artificial dense neural network baseline.