Spectral library transfer between distinct Laser-Induced Breakdown Spectroscopy systems trained on simultaneous measurements

Abstract

The mutual incompatibility of distinct spectroscopic systems is among the most limiting factors in Laser-Induced Breakdown Spectroscopy (LIBS). The cost related to setting up a new LIBS system is increased, as its extensive calibration is required. Solving the problem would enable inter-laboratory reference measurements and shared spectral libraries, which are fundamental for other spectroscopic techniques. We study a simplified version of this challenge where LIBS systems differ only in used spectrometers and collection optics but share all other parts of the apparatus, and collect spectra simultaneously from the same plasma plume. Extensive datasets measured as hyperspectral images of heterogeneous rock sample are used to train machine learning models that can transfer spectra between systems. The transfer is realized by a composed model that consists of a variational autoencoder (VAE) and a multilayer perceptron (MLP). The VAE is used to create a latent representation of spectra from the Primary system. Subsequently, spectra from the Secondary system are mapped to corresponding locations in the latent space by the MLP. The transfer is evaluated by several figures of merit (Euclidean and cosine distances, both spatially resolved; k-means clustering of transferred spectra). We demonstrate the viability of the method and compare it to several baseline approaches of varying complexity.The mutual incompatibility of distinct spectroscopic systems is among the most limiting factors in Laser-Induced Breakdown Spectroscopy (LIBS). The cost related to setting up a new LIBS system is increased, as its extensive calibration is required. Solving the problem would enable inter-laboratory reference measurements and shared spectral libraries, which are fundamental for other spectroscopic techniques. We study a simplified version of this challenge where LIBS systems differ only in used spectrometers and collection optics but share all other parts of the apparatus, and collect spectra simultaneously from the same plasma plume. Extensive datasets measured as hyperspectral images of heterogeneous rock sample are used to train machine learning models that can transfer spectra between systems. The transfer is realized by a composed model that consists of a variational autoencoder (VAE) and a multilayer perceptron (MLP). The VAE is used to create a latent representation of spectra from the Primary system. Subsequently, spectra from the Secondary system are mapped to corresponding locations in the latent space by the MLP. The transfer is evaluated by several figures of merit (Euclidean and cosine distances, both spatially resolved; k-means clustering of transferred spectra). We demonstrate the viability of the method and compare it to several baseline approaches of varying complexity.