Learning Endmember Dynamics in Multitemporal Hyperspectral Data Using a State-Space Model Formulation

TL;DR

This paper introduces a novel state-space model framework for multitemporal hyperspectral unmixing, enabling endmember dynamics learning and integration of prior knowledge, demonstrated through simulated data experiments.

Contribution

It presents a new state-space model approach for multitemporal hyperspectral unmixing, incorporating neural networks for dynamics learning and prior knowledge integration.

Findings

Effective modeling of endmember dynamics in simulated data

Ability to incorporate external prior knowledge

Potential for improved multitemporal unmixing accuracy

Abstract

Hyperspectral image unmixing is an inverse problem aiming at recovering the spectral signatures of pure materials of interest (called endmembers) and estimating their proportions (called abundances) in every pixel of the image. However, in spite of a tremendous applicative potential and the avent of new satellite sensors with high temporal resolution, multitemporal hyperspectral unmixing is still a relatively underexplored research avenue in the community, compared to standard image unmixing. In this paper, we propose a new framework for multitemporal unmixing and endmember extraction based on a state-space model, and present a proof of concept on simulated data to show how this representation can be used to inform multitemporal unmixing with external prior knowledge, or on the contrary to learn the dynamics of the quantities involved from data using neural network architectures adapted to the identification of dynamical systems.