Deep Gaussian Processes for geophysical parameter retrieval
Geophysics
2020-12-23 v1 Machine Learning
Signal Processing
Applications
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.
Keywords
Cite
@article{arxiv.2012.12099,
title = {Deep Gaussian Processes for geophysical parameter retrieval},
author = {Daniel Heestermans Svendsen and Pablo Morales-Álvarez and Rafael Molina and Gustau Camps-Valls},
journal= {arXiv preprint arXiv:2012.12099},
year = {2020}
}
Comments
Preprint, Paper published in IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, 2018, pp. 6175-6178