Machine Learning Methods for the Inversion of Hyperspectral Images
Résumé
In this chapter, the physical analysis of planetary hyperspectral images by massive inversion is addressed. A direct radiative transfer model that relates a given combination of atmospheric or surface parameters to a spectrum is used to build a training set of synthetic observables. The inversion is based on the statistical estimation of the functional relationship between parameters and spectra. To deal with high dimensionality (image cubes typically present hundreds of bands), a two step method is proposed, namely K-GRSIR. It consists of a dimension reduction step followed by a regression with a non-linear least-squares algorithm. The dimension reduction is performed with the Gaussian Regularized Sliced Inverse Regression algorithm, which finds the most relevant directions in the space of synthetic spectra for the regression. The method is compared to several algorithms: a regularized version of k-nearest neighbors, partial least-squares, linear and non-linear support vector machines. Experimental results on simulated data sets have shown that non-linear support vector machines is the most accurate method followed by K-GRSIR. However, when dealing with real data sets, K-GRSIR gives the most interpretable results and is easier to train.
Origine : Fichiers produits par l'(les) auteur(s)