HyperPCA: a powerful tool to extract elemental maps from noisy data obtained in LIBS mapping of materials

Riccardo Finotello (1) , Mohamed Tamaazousti (2) , Jean-Baptiste Sirven (1)

1 LANIE - Laboratoire de développement Analytique Nucléaire Isotopique et Elémentaire
2 DIASI (CEA, LIST) - Département Intelligence Ambiante et Systèmes Interactifs

Laser-induced breakdown spectroscopy (LIBS) is a preferred technique for fast and direct multi-elemental mapping of samples under ambient pressure, without any limitation on the targeted element. However, LIBS mapping data have two peculiarities: an intrinsically low signal-to-noise ratio due to single-shot measurements, and a high dimensionality due to the high number of spectra acquired for imaging. This is all the truer as lateral resolution gets higher: in this case, the ablation spot diameter is reduced, as well as the ablated mass and the emission signal, while the number of spectra for a given surface increases. Therefore, efficient extraction of physico-chemical information from a noisy and large dataset is a major issue. Multivariate approaches were introduced by several authors as a means to cope with such data, particularly Principal Component Analysis (PCA). PCA is useful to analyze correlations between different elements, but it is limited to low signal-to-noise ratios. In this paper, we introduce HyperPCA, a new analysis tool for hyperspectral images based on a sparse representation of the data using Discrete Wavelet Transform (DWT) and kernel-based sparse PCA (kSPCA) to reduce the impact of noise on the data and to consistently extract the spectroscopic signal, with a particular emphasis on LIBS data. The method is first illustrated using simulated LIBS mapping datasets to emphasize its performances with an extremely low shot-to-shot signal-to-noise ratio, and with a variable degree of spectral interference. Comparisons to standard PCA and to traditional univariate data analyses are provided. Finally, it is used to process real data in two cases that clearly illustrate the potential of the proposed algorithm. We show that the method presents advantages both in quantity and quality of the information recovered, thus improving the physico-chemical characterization of analysed surfaces. Recovering the principal components of noisy spectroscopic data is difficult Current PCA approaches show limited efficacy for LIBS mapping data Improvements are introduced through sparse signal representation and kernel-based PCA Noise is reduced by using a kernel function on the entries of the covariance matrix Wavelets mostly group lines of given elements in the same principal components.

Domaines: Machine Learning [stat.ML]; Applications [stat.AP]; Analyse de données, Statistiques et Probabilités [physics.data-an]; Chimie-Physique [physics.chem-ph]; Matériaux; Optique / photonique

Riccardo Finotello, Mohamed Tamaazousti, Jean-Baptiste Sirven. HyperPCA: a powerful tool to extract elemental maps from noisy data obtained in LIBS mapping of materials. Spectrochimica Acta Part B: Atomic Spectroscopy, 2022, 192, pp.106418. ⟨10.1016/j.sab.2022.106418⟩. ⟨cea-03716823⟩