Applications of machine learning in ion beam analysis of materials

Abstract

Ion Beam Analysis (IBA) is an established tool for material characterization, providing precise information on elemental composition, depth profiles, and structural information in the region near the surface of materials. However, traditional data processing methods can be slow and computationally intensive, limiting the efficiency and speed of the analysis. This article explores the current landscape of applying Machine Learning Algorithms (MLA) in the field of IBA, demonstrating the immense potential to optimize and accelerate processes. We present how ML has been employed to extract valuable insights from large datasets, automate repetitive tasks, and enhance the interpretability of results, with practical examples of applications in various IBA techniques, such as RBS, PIXE, and others. Finally, perspectives on using MLA to approach open problems in IBA are also discussed.

9 pages, 3 figures

References in corpus (5)

• Simultaneous PIXE and RBS data analysis using Bayesian Inference with the DataFurnace code
• Predicting electronic stopping powers using stacking ensemble machine learning method
• Processing of massive Rutherford Back-scattering Spectrometry data by artificial neural networks
• ESPNN: A novel electronic stopping power neural-network code built on the IAEA stopping power database. I. Atomic targets
• Ion beam analysis and big data: How data science can support next-generation instrumentation