X-ray Diffraction Data Analysis by Machine Learning Methods—a review
Download 1.51 Mb. Pdf ko'rish
|
applsci-13-09992
Keywords:
X-ray diffraction; phase identification; phase transitions; crystal structure; machine learning; cluster analysis; deep learning; neural networks 1. Introduction Machine learning (ML) has recently found numerous applications, and it is being leveraged as a powerful tool in various fields: computer science, engineering, telecom- munications, chemistry, physics, mathematics, imaging science, materials science, and environmental sciences. The importance of ML is also confirmed by an increasing trend in the volume of work published over the last decade, according to Web of Science data (Figure 1 ). In computer science, ML is used for various tasks, such as natural language process- ing [ 1 – 5 ], image recognition [ 6 – 8 ], or computer vision [ 9 – 14 ]. In engineering, ML is applied in the optimization and control of complex systems [ 15 – 18 ], the prediction of equipment failures [ 19 – 21 ], or the enhancement of manufacturing processes [ 22 – 25 ]. ML is also exten- sively used in materials science for materials discovery [ 26 – 30 ], property prediction [ 31 – 34 ], and accelerated materials design [ 35 – 37 ]. Appl. Sci. 2023, 13, 9992. https://doi.org/10.3390/app13179992 https://www.mdpi.com/journal/applsci Appl. Sci. 2023, 13, 9992 2 of 22 Appl. Sci. 2023, 13, x FOR PEER REVIEW 2 of 22 (a) (b) Figure 1. Number of publications about machine learning, according to Web of Science: (a) yearly publication counts; (b) classification by research area. Understanding materials’ structure, composition, and properties is essential in ex- perimental materials science. Thus, spectroscopy and microscopy are used to characterize the behavior of materials at various scales. The integration of machine learning methods has brought transformative advancements to the analysis of complex data. Several models have been employed to automate the interpretation of intricate spectroscopic data, facili- tating the enhancement of signals, feature extraction, compound classification, and prop- erty prediction. Similarly, these methods have enabled automated particle detection, crys- tallographic analysis, and defect recognition in electron microscopy images, surpassing conventional image processing approaches [38–40]. One example is [41], which showed that deep learning has great potential in perform- ing all the steps and emphasized the importance of addressing the estimation of the pre- diction quality of deep learning models on small datasets with complex covariance struc- tures. Another example is the case of scanning transmission electron microscopy–electron Download 1.51 Mb. Do'stlaringiz bilan baham: |
Ma'lumotlar bazasi mualliflik huquqi bilan himoyalangan ©fayllar.org 2024
ma'muriyatiga murojaat qiling
ma'muriyatiga murojaat qiling