Laser-Induced Breakdown Spectroscopy and Machine Learning for Elemental Analysis
This community develops rapid, non-destructive methods to identify and quantify chemical elements in materials, soils, and industrial products, primarily using laser-induced breakdown spectroscopy (LIBS) and near-infrared spectroscopy.
The work centers on using pulsed lasers to generate plasma from solid or liquid samples, then analyzing the resulting optical emission or infrared spectra to determine elemental composition. Recurring applications include detecting heavy metals in soil, analyzing aluminum alloys, and cleaning surfaces. A significant portion of the research applies machine learning and deep learning algorithms to process spectral data, improving the accuracy of quantitative determinations and enabling the use of hyperspectral imaging for broader material characterization.
The largest share of the community's output is found in yttrium research (1.3% of all yttrium research), followed by neodymium (1.8%) and argon (0.6%). In terms of paper count, yttrium also leads with 1,297 papers, while carbon contributes 988 papers.
The community comprises 14,323 papers, published most frequently in Spectrochimica Acta Part B: Atomic Spectroscopy, Applied Spectroscopy, and the Journal of Applied Physics.
Recent work focuses on combining LIBS with acoustic signals for explainable AI models, applying transfer learning to predict moisture content in agricultural products, and using laser ablation to synthesize nanoparticles for biosensing and antibacterial applications.