Deep Gaussian Processes for geophysical parameter retrieval
This paper addresses the problem of efficiently and accurately retrieving geophysical parameters from large datasets, which is relevant for environmental scientists and meteorologists.
This paper introduces deep Gaussian processes (DGPs) for geophysical parameter retrieval, specifically for estimating surface dew point temperature from infrared sounding data. The DGP model provides an efficient solution that scales well to large datasets and improves prediction accuracy over standard full and sparse GP models.
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.