DeepFit: Physically and Chemically Informed XAS-Structure Fitting Made Simple

Kirill Kulaev

doi:10.1021/acs.jpclett.5c04009

DeepFit: Physically and Chemically Informed XAS-Structure Fitting Made Simple

2026-02-01

0

PRE

AI

DOI：10.1021/acs.jpclett.5c04009

Original

Original request for help

Save

Abstract

En 中文

X-ray absorption spectroscopy (XAS) reveals local structures in catalysts and materials under operando conditions but faces ill-posed challenges, with high computational costs and ambiguous solutions. DeepFit pioneers a universal deep learning remedy, deploying a differentiable minimization of both a spectral mismatch and quantum-chemical energy. The model is based on an E(3)-equivariant neural network trained on the original database of 67,000 theoretical K-edge spectra from diverse 3d/4d transition metal complexes. The approach ensures physically equivariant and chemically plausible refinement of 3D structure and is validated on the experimental case studies for homogeneous catalysts. The benchmark for the series of 3d compounds shows agreement of DeepFit refined bond lengths with respect to XRD/EXAFS (MAE 0.06 & Aring;) and 0.73 ROC-AUC selectivity over local motifs. By merging machine learning spectra approximation and quantum chemical constraints, DeepFit transforms quantitative XAS analysis toward a black-box, routine tool.

Keywords:

ABSORPTION FINE-STRUCTURE

CRYSTAL-STRUCTURE

XANES

EXAFS

SPECTROSCOPY

CATALYST

HYDROGENATION

SYNCHROTRON

COMPLEXES

OPERANDO

DeepFit: Physically and Chemically Informed XAS-Structure Fitting Made Simple

Abstract

Journal

Organization