Evaluating Gaussian processes for sparse irregular spatio-temporal data

TL;DR

This paper introduces a practical method to evaluate Gaussian process regression models on sparse, irregular spatio-temporal data by using a secondary autoregressive model to forecast future observations.

Contribution

The paper proposes a novel evaluation approach for GPR models on irregular data, demonstrated on Ornstein-Uhlenbeck and Fractional processes with varying sparsity levels.

Findings

The evaluation method effectively assesses GPR performance on sparse data.

Different GPR models show varying accuracy depending on data sparsity.

The approach provides insights into the utility of GPR for irregular time-series.

Abstract

A practical approach to evaluate performance of a Gaussian process regression models (GPR) for irregularly sampled sparse time-series is introduced. The approach entails construction of a secondary autoregressive model using the fine scale predictions to forecast a future observation used in GPR. We build different GPR models for Ornstein-Uhlenbeck and Fractional processes for simulated toy data with different sparsity levels to assess the utility of the approach.