• Home
  • Search
  • Deep Gaussian processes for biogeophysical parameter retrieval and model inversion
  • Cite Icon41
  • https://doi.org/10.1016/j.isprsjprs.2020.04.014Copy DOI Icon

Deep Gaussian processes for biogeophysical parameter retrieval and model inversion

Show More
  • Abstract
  • Highlights & Summary
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

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.

Similar Papers
  • Research Article
  • Citations42

Retrieval of Specific Leaf Area From Landsat-8 Surface Reflectance Data Using Statistical and Physical Models

  • Aug 01, 2017
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Abebe Mohammed Ali +2
  • Preprint Article

Advances in Gaussian Processes for Earth Sciences: Physics-aware, interpretability and consistency

  • Mar 23, 2020
  • Gustau Camps-Valls +5
  • Research Article
  • Citations61

Inversion of radiative transfer model for retrieval of wheat biophysical parameters from broadband reflectance measurements

  • Apr 27, 2016
  • Information Processing in Agriculture
  • Vinay Kumar Sehgal +2
  • Research Article
  • Citations233

Mapping grassland leaf area index with airborne hyperspectral imagery: A comparison study of statistical approaches and inversion of radiative transfer models

  • Oct 28, 2011
  • ISPRS Journal of Photogrammetry and Remote Sensing
  • Roshanak Darvishzadeh +3
  • Research Article
  • Citations27

Randomized kernels for large scale Earth observation applications

  • Mar 08, 2017
  • Remote Sensing of Environment
  • Adrián Pérez-Suay +5
  • Conference Article
  • Citations6

Application of vegetation isoline equations for simultaneous retrieval of leaf area index and leaf chlorophyll content using reflectance of red edge band

  • Sep 19, 2016
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Kakuya Okuda +4
  • PDF
  • Research Article
  • Citations15

Evaluating Prediction Models for Mapping Canopy Chlorophyll Content Across Biomes

  • Jun 01, 2020
  • Remote Sensing
  • Abebe Mohammed Ali +6
  • Research Article
  • Citations27

Visualizing the ill-posedness of the inversion of a canopy radiative transfer model: A case study for Sentinel-2

  • Feb 25, 2015
  • International Journal of Applied Earth Observation and Geoinformation
  • R Zurita-Milla +2
  • Research Article
  • Citations32

Empirical Assessment of Deep Gaussian Process Surrogate Models for Engineering Problems

  • Sep 18, 2020
  • Journal of Aircraft
  • Dushhyanth Rajaram +6
  • Research Article
  • Citations64

Machine learning methods’ performance in radiative transfer model inversion to retrieve plant traits from Sentinel-2 data of a mixed mountain forest

  • Jul 15, 2020
  • International Journal of Digital Earth
  • Abebe Mohammed Ali +4
  • PDF
  • Research Article
  • Citations98

Efficient Emulation of Radiative Transfer Codes Using Gaussian Processes and Application to Land Surface Parameter Inferences

  • Feb 05, 2016
  • Remote Sensing
  • José Gómez-Dans +2
  • Research Article

Retrieval of crop biophysical and biochemical traits using airborne hyperspectral observations and inversion of radiative transfer models over diverse cropping regions

  • Jul 19, 2026
  • International Journal of Remote Sensing
  • Radhika Lalitkumar Ghetiya +2
  • Research Article
  • Citations168

Comparative analysis of different retrieval methods for mapping grassland leaf area index using airborne imaging spectroscopy

  • Jan 29, 2015
  • International Journal of Applied Earth Observation and Geoinformation
  • Clement Atzberger +5
  • PDF
  • Research Article
  • Citations24

Landsat-8 and Sentinel-2 Canopy Water Content Estimation in Croplands through Radiative Transfer Model Inversion

  • Aug 29, 2020
  • Remote Sensing
  • Erik J Boren +1
  • Research Article
  • Citations79

Improving the Robustness of Cotton Status Characterisation by Radiative Transfer Model Inversion of Multi-Angular CHRIS/PROBA Data

  • Feb 01, 2012
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Wouter A Dorigo
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.