Consistent regression of biophysical parameters with kernel methods

TL;DR

This paper presents a new kernel-based regression framework that enforces consistency constraints, effectively estimating biophysical parameters like chlorophyll content while maintaining independence from protected variables.

Contribution

The paper introduces a novel regression method with closed-form solutions that incorporate consistency constraints and independence from auxiliary variables.

Findings

Effective estimation of chlorophyll content demonstrated

Models exploit all driver information efficiently

Framework maintains independence from protected variables

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.