Red Teaming Models for Hyperspectral Image Analysis Using Explainable AI

TL;DR

This paper presents a novel explainable AI-based red teaming methodology for hyperspectral image analysis, identifying model flaws, reducing feature reliance, and improving interpretability for space remote sensing applications.

Contribution

It introduces a red teaming approach using XAI techniques to evaluate and improve hyperspectral ML models, including a new visualization method tailored for spectral data.

Findings

Identified key model shortcomings through red teaming.

Reduced input features to 1% with minimal performance loss.

Developed a domain-specific explanation visualization method.

Abstract

Remote sensing (RS) applications in the space domain demand machine learning (ML) models that are reliable, robust, and quality-assured, making red teaming a vital approach for identifying and exposing potential flaws and biases. Since both fields advance independently, there is a notable gap in integrating red teaming strategies into RS. This paper introduces a methodology for examining ML models operating on hyperspectral images within the HYPERVIEW challenge, focusing on soil parameters' estimation. We use post-hoc explanation methods from the Explainable AI (XAI) domain to critically assess the best performing model that won the HYPERVIEW challenge and served as an inspiration for the model deployed on board the INTUITION-1 hyperspectral mission. Our approach effectively red teams the model by pinpointing and validating key shortcomings, constructing a model that achieves comparable performance using just 1% of the input features and a mere up to 5% performance loss. Additionally, we propose a novel way of visualizing explanations that integrate domain-specific information about hyperspectral bands (wavelengths) and data transformations to better suit interpreting models for hyperspectral image analysis.