Harnessing Neural Networks for Elucidating X-ray Absorption Structure–Spectrum Relationships in Amorphous Carbon

Abstract

Improved understanding of structural and chemical properties through local experimental probes, such as X-ray absorption near-edge structure (XANES) spectroscopy, is crucial for the understanding and design of functional materials. In recent years, significant advancements have been made in the development of data science approaches for the automated interpretation of XANES structure−spectrum relationships. However, existing studies have primarily focused on crystalline solids and small molecules, while fewer efforts have been devoted to disordered systems. Thus, in this work, we demonstrate the development of neural network models for predicting and interpreting XANES spectra of amorphous carbon (a-C) from local structural descriptors. Comparison between different structural descriptors expectedly shows that the inclusion of both bond length and bond angle information is necessary for an accurate prediction of the spectra. Among the descriptors considered in this work, we find that the local many-body tensor representation yields the highest accuracy and greatest interpretability so that it can be leveraged to understand the importance of structural motifs in determining XANES spectra. We also discuss performance of neural network models for predicting both local structure features, such as bond lengths and bond angles, and global chemical composition, such as the sp:sp 2 :sp 3 ratio.

Integrating Machine Learning Potential and X-ray Absorption Spectroscopy for Predicting the Chemical Speciation of Disordered Carbon Nitrides

“…The FCH technique is analogous to the XCH adopted here except that it neglects a self-consistent inclusion of the excited electron. While a thorough comparison on the performance of different approximations requires a more extensive study, our initial tests for simple systems, including diamond and graphite, show that the XCH approximation reasonably reproduces the main features of experimental spectra of these systems . A better agreement between DFT simulations and experiment can be achieved by improving the level of theory, such as Bethe–Salpeter calculations that explicitly account for the electron and core-hole interaction, − which is beyond the scope of this work.…”

Accurate, Uncertainty-Aware Classification of Molecular Chemical Motifs from Multimodal X-ray Absorption Spectroscopy

“…29,55 The π*/σ* intensity ratio is found to be an effective descriptor for differentiating sp from sp 2 carbon sites, with a higher ratio for sp carbon. 55 Our spectra yield a consistent trend with a higher π*/σ* intensity ratio in alkynes than that in alkenes and aromatic carbons. However, the contrast is weaker in our data due to different levels of theory in this study and ref 55. In Figure 2a, we plot the PCA decomposition of N and O (gray area) overlaid with four chemical motifs similar to Figure 1.…”

“…As expected, the average spectra of alkene and aromatic carbons are very similar to each other, which is reflected in the significant overlap of their PCA patterns from (ii) and (iv). Aarva et al and Kwon et al developed computational C K-edge XANES databases of amorphous carbon based on the first-principles excited core-hole method. The analysis shows overall distinct spectral features of carbon with different coordination numbers. , The π*/σ* intensity ratio is found to be an effective descriptor for differentiating sp from sp 2 carbon sites, with a higher ratio for sp carbon .…”

“…Aarva et al and Kwon et al developed computational C K-edge XANES databases of amorphous carbon based on the first-principles excited core-hole method. The analysis shows overall distinct spectral features of carbon with different coordination numbers. , The π*/σ* intensity ratio is found to be an effective descriptor for differentiating sp from sp 2 carbon sites, with a higher ratio for sp carbon . Our spectra yield a consistent trend with a higher π*/σ* intensity ratio in alkynes than that in alkenes and aromatic carbons.…”

“…Our spectra yield a consistent trend with a higher π*/σ* intensity ratio in alkynes than that in alkenes and aromatic carbons. However, the contrast is weaker in our data due to different levels of theory in this study and ref .…”