Deep learning with laser-induced breakdown spectroscopy (LIBS) for the classification of rocks based on elemental imaging

• Published in: Applied geochemistry Vol. 136; p. 105135
• Main Authors: Chen, Tong, Sun, Lanxiang, Yu, Haibin, Wang, Wei, Qi, Lifeng, Zhang, Peng, Zeng, Peng
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.01.2022
• Subjects: atomic absorption spectrometry; Data augmentation; data collection; elemental composition; evolution; geochemistry; gneiss; granite; Inception-v3 net; LIBS-Based imaging; liquids; lithology; paleontology; Rock classification; shale; Transfer learning; Data augmentation; LIBS-Based imaging; Rock classification; Inception-v3 net; Transfer learning
• ISSN: 0883-2927; 1872-9134
• DOI: 10.1016/j.apgeochem.2021.105135

In geological research, the identification and classification of rock lithology plays an important role in many fields such as resource exploration, earth evolution and paleontology research. Laser-induced breakdown spectroscopy (LIBS), which is capable of real-time, on-situ, micro-destructive determination of the elemental composition of any substance (solid, liquid, or gas), has been developed as a technology for ‘geochemical fingerprinting’ in a variety of geochemical applications. However, for rock samples with coarse grains, the bulk analysis based on the average spectrum is insufficient. This study proposes a new method for identifying multiple types of rocks, which utilizes the rapid multi-element compositional imaging capability of LIBS, and combines with the deep learning theory. The LIBS-based images characterizing the spatial distribution of elements on rock surface were achieved firstly, and then were classified by the Inception-v3 network combined with the transfer learning method. In addition, to solve the problem of the small scale of the image dataset obtained in the laboratory, specific data augmentation methods such as cutting-recombining and filtering were proposed. Moreover, the superior of this method was verified by the three classification experiments of shale, gneiss and granite. [Display omitted] •Utilized the LIBS-based imaging.•Combined with the deep learning theory.•Proposed specific data augmentation methods.