elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

An Overview of Neural Network Methods for Predicting Uncertainty in Atmospheric Remote Sensing

Doicu, A. and Doicu, Alexandru and Efremenko, Dmitry and Loyola, Diego and Trautmann, Thomas (2021) An Overview of Neural Network Methods for Predicting Uncertainty in Atmospheric Remote Sensing. Remote Sensing, 13 (24), p. 5061. Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/rs13245061. ISSN 2072-4292.

[img] PDF - Published version
698kB

Official URL: http://dx.doi.org/10.3390/rs13245061

Abstract

In this paper, we present neural network methods for predicting uncertainty in atmospheric remote sensing. These include methods for solving the direct and the inverse problem in a Bayesian framework. In the first case, a method based on a neural network for simulating the radiative transfer model and a Bayesian approach for solving the inverse problem is proposed. In the second case, (i) a neural network, in which the output is the convolution of the output for a noise-free input with the input noise distribution; and (ii) a Bayesian deep learning framework that predicts input aleatoric and model uncertainties, are designed. In addition, a neural network that uses assumed density filtering and interval arithmetic to compute uncertainty is employed for testing purposes. The accuracy and the precision of the methods are analyzed by considering the retrieval of cloud parameters from radiances measured by the Earth Polychromatic Imaging Camera (EPIC) onboard the Deep Space Climate Observatory (DSCOVR).

Item URL in elib:https://elib.dlr.de/147553/
Document Type:Article
Title:An Overview of Neural Network Methods for Predicting Uncertainty in Atmospheric Remote Sensing
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Doicu, A.Adrian.Doicu (at) dlr.deUNSPECIFIED
Doicu, AlexandruAugsburg UniversityUNSPECIFIED
Efremenko, DmitryDmitry.Efremenko (at) dlr.dehttps://orcid.org/0000-0002-7449-5072
Loyola, DiegoDiego.Loyola (at) dlr.dehttps://orcid.org/0000-0002-8547-9350
Trautmann, ThomasThomas.Trautmann (at) dlr.deUNSPECIFIED
Date:2021
Journal or Publication Title:Remote Sensing
Refereed publication:Yes
Open Access:Yes
Gold Open Access:Yes
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:13
DOI :10.3390/rs13245061
Page Range:p. 5061
Publisher:Multidisciplinary Digital Publishing Institute (MDPI)
ISSN:2072-4292
Status:Published
Keywords:neural networks; interval arithmetic; radiative transfer
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Spectroscopic methods of the atmosphere
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Atmospheric Processors
Deposited By: Efremenko, Dr Dmitry
Deposited On:15 Dec 2021 12:34
Last Modified:21 Dec 2021 11:38

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.