Deep Gaussian Processes for geophysical parameter retrieval

TL;DR

This paper presents deep Gaussian processes (DGPs) as an advanced method for geophysical parameter retrieval, demonstrating improved accuracy and scalability over traditional Gaussian process models, with empirical validation on infrared sounding data.

Contribution

The paper introduces DGPs for geophysical retrieval, offering a scalable, hierarchical approach that outperforms standard GP models in accuracy.

Findings

DGPs improve prediction accuracy over standard GPs.

DGPs scale efficiently to large datasets.

Empirical validation on infrared data shows enhanced performance.

Abstract

This paper introduces deep Gaussian processes (DGPs) for geophysical parameter retrieval. Unlike the standard full GP model, the DGP accounts for complicated (modular, hierarchical) processes, provides an efficient solution that scales well to large datasets, and improves prediction accuracy over standard full and sparse GP models. We give empirical evidence of performance for estimation of surface dew point temperature from infrared sounding data.