Advanced 2D-PIXE/RBS processing with Machine Learning at the New AGLAE facility for ancient layered objects

IF 1.4 3区物理与天体物理 Q3 INSTRUMENTS & INSTRUMENTATION

Nuclear Instruments & Methods in Physics Research Section B-beam Interactions With Materials and Atoms Pub Date : 2024-07-23 DOI:10.1016/j.nimb.2024.165469

Astrid Tazzioli , Quentin Lemasson , Alexandre Girard , Laurent Pichon , Brice Moignard , Claire Pacheco

{"title":"Advanced 2D-PIXE/RBS processing with Machine Learning at the New AGLAE facility for ancient layered objects","authors":"Astrid Tazzioli , Quentin Lemasson , Alexandre Girard , Laurent Pichon , Brice Moignard , Claire Pacheco","doi":"10.1016/j.nimb.2024.165469","DOIUrl":null,"url":null,"abstract":"<div><p>Studying without sampling the fine layering of heritage objects, usually heterogeneous in composition and with an uneven surface requires new methodologies. Single spot analyses are not representative and may lead to misinterpretation; thus, they are not sufficient to conclude on the layering. 2D-imaging is essential to analyze a bigger area to recover the characteristics of heritage objects. However, processing 2D-RBS images pixel per pixel requires a long computing time. To automate the processing of 2D-IBA images at New AGLAE, the use of artificial intelligence enables the consideration of all the spectra from the different detectors and across the entire area simultaneously. Unsupervised learning algorithms for clustering bring together the pixels with similar characteristics, effectively capturing the essential features of the 2D-images. The signal corresponding to each cluster can then be processed to obtain both the chemical composition and layer thicknesses of the analyzed areas. Thus, a spatial distribution of the stratigraphy is obtained.</p></div>","PeriodicalId":19380,"journal":{"name":"Nuclear Instruments & Methods in Physics Research Section B-beam Interactions With Materials and Atoms","volume":"555 ","pages":"Article 165469"},"PeriodicalIF":1.4000,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nuclear Instruments & Methods in Physics Research Section B-beam Interactions With Materials and Atoms","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0168583X24002398","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"INSTRUMENTS & INSTRUMENTATION","Score":null,"Total":0}

引用次数: 0

Abstract

Studying without sampling the fine layering of heritage objects, usually heterogeneous in composition and with an uneven surface requires new methodologies. Single spot analyses are not representative and may lead to misinterpretation; thus, they are not sufficient to conclude on the layering. 2D-imaging is essential to analyze a bigger area to recover the characteristics of heritage objects. However, processing 2D-RBS images pixel per pixel requires a long computing time. To automate the processing of 2D-IBA images at New AGLAE, the use of artificial intelligence enables the consideration of all the spectra from the different detectors and across the entire area simultaneously. Unsupervised learning algorithms for clustering bring together the pixels with similar characteristics, effectively capturing the essential features of the 2D-images. The signal corresponding to each cluster can then be processed to obtain both the chemical composition and layer thicknesses of the analyzed areas. Thus, a spatial distribution of the stratigraphy is obtained.

查看原文本刊更多论文

AGLAE 新设施利用机器学习技术对古代层状物体进行先进的二维-PIXE/RBS 处理

要在不取样的情况下研究文物的细微分层，需要采用新的方法，这些文物通常成分不同，表面凹凸不平。单点分析不具代表性，可能导致误读，因此不足以得出分层结论。二维成像对于分析更大区域以恢复文物特征至关重要。然而，处理 2D-RBS 图像的每个像素需要较长的计算时间。为了在新 AGLAE 实现 2D-IBA 图像的自动化处理，人工智能的使用可以同时考虑来自不同探测器和整个区域的所有光谱。用于聚类的无监督学习算法将具有相似特征的像素聚集在一起，有效捕捉二维图像的基本特征。然后，可以对每个聚类对应的信号进行处理，以获得分析区域的化学成分和地层厚度。这样，就得到了地层的空间分布情况。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Nuclear Instruments & Methods in Physics Research Section B-beam Interactions With Materials and Atoms 物理-核科学技术

CiteScore

2.80

自引率

7.70%

发文量

231

审稿时长

1.9 months

期刊介绍： Section B of Nuclear Instruments and Methods in Physics Research covers all aspects of the interaction of energetic beams with atoms, molecules and aggregate forms of matter. This includes ion beam analysis and ion beam modification of materials as well as basic data of importance for these studies. Topics of general interest include: atomic collisions in solids, particle channelling, all aspects of collision cascades, the modification of materials by energetic beams, ion implantation, irradiation - induced changes in materials, the physics and chemistry of beam interactions and the analysis of materials by all forms of energetic radiation. Modification by ion, laser and electron beams for the study of electronic materials, metals, ceramics, insulators, polymers and other important and new materials systems are included. Related studies, such as the application of ion beam analysis to biological, archaeological and geological samples as well as applications to solve problems in planetary science are also welcome. Energetic beams of interest include atomic and molecular ions, neutrons, positrons and muons, plasmas directed at surfaces, electron and photon beams, including laser treated surfaces and studies of solids by photon radiation from rotating anodes, synchrotrons, etc. In addition, the interaction between various forms of radiation and radiation-induced deposition processes are relevant.