Interpretable Multimodal Machine Learning Analysis of X-ray Absorption Near-Edge Spectra and Pair Distribution Functions

Abstract

We used interpretable machine learning to combine information from multiple heterogeneous spectra: X-ray absorption near-edge spectra (XANES) and atomic pair distribution functions (PDFs) to extract local structural and chemical environments of transition metal cations in oxides. Random forest models were trained on simulated XANES, PDF, and both combined to extract oxidation state, coordination number, and mean nearest-neighbor bond length. XANES-only models generally outperformed PDF-only models, even for structural tasks, although using the metal's differential PDFs (dPDFs) instead of total PDFs narrowed this gap. When combined with PDFs, information from XANES often dominates the prediction. Our results demonstrate that XANES contain rich structural information and highlight the utility of species-specificity. This interpretable, multimodal approach is quick to implement with suitable databases and offers valuable insights into the relative strengths of different modalities, guiding researchers in experiment design and identifying when combining complementary techniques adds meaningful information to a scientific investigation.

References in corpus (5)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Classification of Local Chemical Environments from X-ray Absorption Spectra using Supervised Machine Learning
• Machine learning based approach for solving atomic structures of nanomaterials combining pair distribution functions with density functional theory
• Decoding Structure-Spectrum Relationships with Physically Organized Latent Spaces
• Robustness test of the spacegroupMining model for determining space groups from atomic pair distribution function data

Cited by in corpus (1)

• Machine Learning-Driven Crystal System Prediction for Perovskites Using Augmented X-ray Diffraction Data