6533b851fe1ef96bd12a9958
RESEARCH PRODUCT
Deep Gaussian processes for biogeophysical parameter retrieval and model inversion
Gustau Camps-vallsDaniel Heestermans SvendsenRafael MolinaAna B. RuescasPablo Morales-alvarezsubject
Signal Processing (eess.SP)FOS: Computer and information sciencesComputer Science - Machine LearningEarth observation010504 meteorology & atmospheric sciencesIASIComputer science0211 other engineering and technologiesExtrapolation02 engineering and technologyDeep Gaussian Processes01 natural sciencesArticleMachine Learning (cs.LG)symbols.namesakeCopernicus programmeSentinelsMachine learningRadiative transferFOS: Electrical engineering electronic engineering information engineeringElectrical Engineering and Systems Science - Signal ProcessingComputers in Earth SciencesModel inversionStatistical retrievalEngineering (miscellaneous)Gaussian processChlorophyll contentMoisture021101 geological & geomatics engineering0105 earth and related environmental sciencesbusiness.industryInorganic suspended matterTemperatureInversion (meteorology)Statistical modelAtomic and Molecular Physics and OpticsComputer Science ApplicationsInfrared sounderNonlinear systemsymbolsGlobal Positioning SystemColoured dissolved matterbusinessAlgorithmdescription
Parameter retrieval and model inversion are key problems in remote sensing and Earth observation. Currently, different approximations exist: a direct, yet costly, inversion of radiative transfer models (RTMs); the statistical inversion with in situ data that often results in problems with extrapolation outside the study area; and the most widely adopted hybrid modeling by which statistical models, mostly nonlinear and non-parametric machine learning algorithms, are applied to invert RTM simulations. We will focus on the latter. Among the different existing algorithms, in the last decade kernel based methods, and Gaussian Processes (GPs) in particular, have provided useful and informative solutions to such RTM inversion problems. This is in large part due to the confidence intervals they provide, and their predictive accuracy. However, RTMs are very complex, highly nonlinear, and typically hierarchical models, so that very often a single (shallow) GP model cannot capture complex feature relations for inversion. This motivates the use of deeper hierarchical architectures, while still preserving the desirable properties of GPs. This paper introduces the use of deep Gaussian Processes (DGPs) for bio-geo-physical model inversion. Unlike shallow GP models, DGPs account for complicated (modular, hierarchical) processes, provide an efficient solution that scales well to big datasets, and improve prediction accuracy over their single layer counterpart. In the experimental section, we provide empirical evidence of performance for the estimation of surface temperature and dew point temperature from infrared sounding data, as well as for the prediction of chlorophyll content, inorganic suspended matter, and coloured dissolved matter from multispectral data acquired by the Sentinel-3 OLCI sensor. The presented methodology allows for more expressive forms of GPs in big remote sensing model inversion problems.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2020-01-01 |