6533b854fe1ef96bd12af364
RESEARCH PRODUCT
Deep Gaussian Processes for Geophysical Parameter Retrieval
Gustau Camps-vallsDaniel Heestermans SvendsenPablo Morales-alvarezRafael Molinasubject
Surface (mathematics)Signal Processing (eess.SP)FOS: Computer and information sciencesComputer Science - Machine Learning010504 meteorology & atmospheric sciencesComputer science0211 other engineering and technologiesFOS: Physical sciences02 engineering and technologyAtmospheric model01 natural sciencesStatistics - ApplicationsMachine Learning (cs.LG)Physics - Geophysicssymbols.namesakeKernel (linear algebra)FOS: Electrical engineering electronic engineering information engineeringApplications (stat.AP)Electrical Engineering and Systems Science - Signal ProcessingGaussian process021101 geological & geomatics engineering0105 earth and related environmental sciencesbusiness.industryGeophysics (physics.geo-ph)Depth soundingDew pointsymbolsGlobal Positioning SystembusinessAlgorithmdescription
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.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2018-07-01 | IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium |