Gaussian graphical modeling for spectrometric data analysis

TL;DR

This paper introduces a Bayesian Gaussian graphical model tailored for spectrometric data, enabling simultaneous smoothing of spectra and estimation of the conditional independence structure among spectral bands.

Contribution

It presents a novel approach combining functional data analysis with Gaussian graphical models to analyze spectrometric data with sparsity in the precision matrix.

Findings

Successfully applied to strawberry puree spectra

Achieved sparse precision matrices indicating spectral dependencies

Enhanced spectral data interpretation through graphical modeling

Abstract

Motivated by the analysis of spectrometric data, we introduce a Gaussian graphical model for learning the dependence structure among frequency bands of the infrared absorbance spectrum. The spectra are modeled as continuous functional data through a B-spline basis expansion and a Gaussian graphical model is assumed as a prior specification for the smoothing coefficients to induce sparsity in their precision matrix. Bayesian inference is carried out to simultaneously smooth the curves and to estimate the conditional independence structure between portions of the functional domain. The proposed model is applied to the analysis of infrared absorbance spectra of strawberry purees.