Consistent regression of biophysical parameters with kernel methods
Methodology
2020-12-10 v1 Machine Learning
Machine Learning
Abstract
This paper introduces a novel statistical regression framework that allows the incorporation of consistency constraints. A linear and nonlinear (kernel-based) formulation are introduced, and both imply closed-form analytical solutions. The models exploit all the information from a set of drivers while being maximally independent of a set of auxiliary, protected variables. We successfully illustrate the performance in the estimation of chlorophyll content.
Cite
@article{arxiv.2012.04922,
title = {Consistent regression of biophysical parameters with kernel methods},
author = {Emiliano Díaz and Adrián Pérez-Suay and Valero Laparra and Gustau Camps-Valls},
journal= {arXiv preprint arXiv:2012.04922},
year = {2020}
}
Comments
arXiv admin note: substantial text overlap with arXiv:1710.05578