Neural networks for the dimensionality reduction of GOME measurement vector in the estimation of ozone profiles |
| |
Authors: | F Del Frate M Iapaolo S Godin-Beekmann |
| |
Institution: | a Dipartimento di Informatica Sistemi e Produzione, Università Tor Vergata, Viadel Politecnico 1, I-00133 Rome, Italy b Institut for Geophysics, Karl Franzens University of Graz, c/o ESA/ESRIN, Via G. Galilei, I-00044 Rome, Italy c Institut Pierre Simon Laplace, Service d'Aéronomie, UPMC - Boite 102, 4 Place Jussieu, 75252 Paris Cedex 05, France d Institut Pierre Simon Laplace, Centre d'étude des Environnements Terrestre et Planétaires, 10-12 Avenue de l'Europe, 78140 Vélizy, France |
| |
Abstract: | Dimensionality reduction can be of crucial importance in the application of inversion schemes to atmospheric remote sensing data. In this study the problem of dimensionality reduction in the retrieval of ozone concentration profiles from the radiance measurements provided by the instrument Global Ozone Monitoring Experiment (GOME) on board of ESA satellite ERS-2 is considered. By means of radiative transfer modelling, neural networks and pruning algorithms, a complete procedure has been designed to extract the GOME spectral ranges most crucial for the inversion. The quality of the resulting retrieval algorithm has been evaluated by comparing its performance to that yielded by other schemes and co-located profiles obtained with lidar measurements. |
| |
Keywords: | Ozone profiles retrieval GOME Neural networks |
本文献已被 ScienceDirect 等数据库收录! |
|