Probabilistic Emissivity Retrieval from Hyperspectral Data via Physics-Guided Variational Inference

TL;DR

This paper introduces a physics-guided probabilistic model for hyperspectral emissivity retrieval that incorporates scene context, enabling interpretable uncertainty quantification and more flexible material identification compared to traditional neural network approaches.

Contribution

It develops a physics-conditioned generative model that estimates emissivity distributions from hyperspectral data, integrating scene context and avoiding training set bias.

Findings

The model provides physically consistent emissivity estimates with uncertainty quantification.

It outperforms traditional methods in material matching accuracy.

The approach enables interpretable probabilistic analysis of hyperspectral data.

Abstract

Recent research has proven neural networks to be a powerful tool for performing hyperspectral imaging (HSI) target identification. However, many deep learning frameworks deliver a single material class prediction and operate on a per-pixel basis; such approaches are limited in their interpretability and restricted to predicting materials that are accessible in available training libraries. In this work, we present an inverse modeling approach in the form of a physics-conditioned generative model.A probabilistic latent-variable model learns the underlying distribution of HSI radiance measurements and produces the conditional distribution of the emissivity spectrum. Moreover, estimates of the HSI scene's atmosphere and background are used as a physically relevant conditioning mechanism to contextualize a given radiance measurement during the encoding and decoding processes. Furthermore, we employ an in-the-loop augmentation scheme and physics-based loss criteria to avoid bias towards a predefined training material set and to encourage the model to learn physically consistent inverse mappings. Monte-Carlo sampling of the model's conditioned posterior delivers a sought emissivity distribution and allows for interpretable uncertainty quantification. Moreover, a distribution-based material matching scheme is presented to return a set of likely material matches for an inferred emissivity distribution. Hence, we present a strategy to incorporate contextual information about a given HSI scene, capture the possible variation of underlying material spectra, and provide interpretable probability measures of a candidate material accounting for given remotely-sensed radiance measurement.