Artificial Neural Networks for Material Identification, Mineralogy and Analytical Geochemistry Based on Laser-Induced Breakdown Spectroscopy

A neural network approach for spatial variation assessment – A nepheline syenite case study

“…Pattern recognition or machine-learning techniques, like artificial neural networks, have been used in identification, prediction and control of properties (Bishop, 2016;Demuth et al, 2014;Goodfellow et al, 2016;Masters, 1993) in a broad variety of fields like banking, data mining, climate and medicine. In the case of mineralogical and mineral processing studies, machinelearning techniques such as neural networks have been used in mineral classification based on X-ray data (Gallagher and Deacon, 2002;Koujelev and Lui, 2011;Rozel et al, 2014;Tsuji et al, 2010), mineral recognition in a frame of geometallurgy (Koch et al, 2019;Leroy and Pirard, 2019;Pérez-Barnuevo et al, 2018), in mineral exploration (Rigol-Sanchez et al, 2003), and to relate spatially processing performance with ore characteristics (Lishchuk et al, 2019;Rajabinasab and Asghari, 2018).…”

Self-absorption correction: an effective approach for precise quantitative analysis with laser induced breakdown spectroscopy

“…In recent years, laser induced breakdown spectroscopy (LIBS) has become a very attractive analytical technique in different areas such as the environment [1,2], geology, space [3,4], art work, jewelry [5,6], and many other fields [7][8][9][10][11]. Compared with other atomic emission spectral analyses, LIBS has many advantages including short measurement time, no or minimal sample preparation, versatility in sample type, and qualitative and quantitative multi-element analysis [12,13].…”