Linear Regression Models and Neural Networks for the Fast Emulation of a Molecular Absorption Code

Guillaume Euvrard 1, * Isabelle Rivals 1 Thierry Huet 2 Sidonie Lefebvre 2 Pierre Simoneau 2
* Corresponding author
1 ESA - Equipe de Statistique Appliquée
2 ONERA - The French Aerospace Lab [Châtillon]
Abstract : The background scene generator MATISSE, whose main functionality is to generate natural background radiance images, makes use of the so-called Correlated K (CK) model. It necessitates either to load or to compute thousands of CK coefficients for each atmospheric profile. When the CK coefficients cannot be loaded, the computation time becomes prohibitive. The idea developed in this paper is to substitute fast approximate models to the exact CK generator: using the latter, a representative set of numerical examples is built and used to train linear or nonlinear regression models. The resulting models enable an accurate CK coefficient computation for all the profiles of an image in a reasonable time.
Keywords : Numerical approximation and analysis Absorption Radiative transfer Neural networks Atmospheric propagation 110.2960 Image analysis
Document type :
Journal articles
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download
https://hal-espci.archives-ouvertes.fr/hal-00805086
Contributor : Isabelle Rivals <>
Submitted on : Wednesday, March 27, 2013 - 8:00:42 AM
Last modification on : Thursday, July 4, 2019 - 11:00:06 AM
Long-term archiving on : Friday, June 28, 2013 - 4:04:59 AM

File

77411F28-BDB9-137E-CA4F0579819...
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-00805086, version 1

Collections

ONERA | ESPCI | PARISTECH | ESA | PSL

Citation

Guillaume Euvrard, Isabelle Rivals, Thierry Huet, Sidonie Lefebvre, Pierre Simoneau. Linear Regression Models and Neural Networks for the Fast Emulation of a Molecular Absorption Code. Applied optics, Optical Society of America, 2009, 48 (35), pp.6770-6780. ⟨hal-00805086⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

564

Files downloads

244

Contact

CCSD