6533b7cefe1ef96bd12571d9
RESEARCH PRODUCT
Disentangling Derivatives, Uncertainty and Error in Gaussian Process Models
Gustau Camps-vallsJuan Emmanuel JohnsonValero Laparrasubject
FOS: Computer and information sciencesComputer Science - Machine Learning010504 meteorology & atmospheric sciencesComputer science0211 other engineering and technologiesMachine Learning (stat.ML)02 engineering and technology01 natural sciencesMachine Learning (cs.LG)symbols.namesakeStatistics - Machine LearningGaussian process021101 geological & geomatics engineering0105 earth and related environmental sciencesVariance functionPropagation of uncertaintyVariance (accounting)Function (mathematics)Confidence intervalNonlinear systemNoiseKernel method13. Climate actionKernel (statistics)symbolsAlgorithmdescription
Gaussian Processes (GPs) are a class of kernel methods that have shown to be very useful in geoscience applications. They are widely used because they are simple, flexible and provide very accurate estimates for nonlinear problems, especially in parameter retrieval. An addition to a predictive mean function, GPs come equipped with a useful property: the predictive variance function which provides confidence intervals for the predictions. The GP formulation usually assumes that there is no input noise in the training and testing points, only in the observations. However, this is often not the case in Earth observation problems where an accurate assessment of the instrument error is usually available. In this paper, we showcase how the derivative of a GP model can be used to provide an analytical error propagation formulation and we analyze the predictive variance and the propagated error terms in a temperature prediction problem from infrared sounding data.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2020-12-09 | IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium |