Julien Brajard

Learn More
This paper presents a new development of the NeuroVaria method. NeuroVaria computes relevant atmospheric and oceanic parameters by minimizing the difference between the observed satellite reflectances and those computed from radiative transfer simulations modelled by artificial neural networks. Aerosol optical properties are computed using the Junge size(More)
RÉSUMÉ Nous nous intéressons à la classification d'individus décrits par des variables mixtes structurées en blocs. Nous proposons une méthode de type hiérarchique en deux étapes pour obtenir une typologie des individus. Elle repose sur une combinaison des cartes topologiques mixtes et de la classification hiérarchique ascendante. La méthode proposée permet(More)
This paper presents a statistical inversion method used to infer 3D data from 2D imaging. The methodology is based on a combination of the Self Organising Maps and the Hidden Markov Models. The Self-Organising Maps generate the typical situations of the emissions and the hidden states of the Hidden Markov Model. The method has been validated by inferring(More)
— The present work addresses the problem of validation of a synthetic dataset with respect to observations. It gives an index that determines locally how much a region of the synthetic dataset fits the observations. The method uses an estimation of the probability density function computed with the probabilistic self-organizing maps. Then, an index F was(More)
  • 1