Machine-learning test of the single-ion model for dd excitations in cuprates
Abstract
We investigate dd excitations in Resonant Inelastic X-ray Scattering spectra of YBa2Cu3O6 and La2CuO4 using the local single-ion model. The data are analyzed by conventional global fitting and by a convolutional neural network trained within the same theoretical framework. For YBa2Cu3O6, the excited state energies obtained with the two methods coincide, leading to the xy, 3z2−r2, xz/yz sequence for increasing energy. This result validates the use of machine learning tools for the analysis of RIXS spectra dominated by dd excitations. By contrast, for La2CuO4, the two methods do not converge to a single solution, revealing the limitations of the single-ion model in describing dd excitations in cuprates and pointing to the role of additional contributions beyond a purely local picture in shaping high-energy excitations.
Versions
Related
- Nonadiabatic excited-state dynamics with quantum Monte Carlo-trained machine learning: azomethane as a stringent test
- PTED: A multi-dimensional two-sample test for scientific inference and generative machine learning
- Pulse-shape discrimination with machine learning for CZT detectors at the DAΦNE beam test facility
- Wisevolve Potential Engine: Machine-Learning Molecular Dynamics at 100 Million Atom-Steps per Second on a Single GPU
- From Heuristics to Machine Learning: The Performance Ceiling for Single-Ion Magnets and Its Electronic Origin
BibTeX
@misc{zinouyeva2026machinelearning,
title = {{Machine-learning test of the single-ion model for $dd$ excitations in cuprates}},
author = {Maryia Zinouyeva and Leonardo Martinelli and Riccardo Arpaia and Nicholas B. Brookes and Daniele Di Castro and Kurt Kummer and Floriana Lombardi and Giacomo Merzoni and Francesco Rosa and Alessandro Tarasio and Enrico Tassi and Flora Yakhou-Harris and Ezio Puppin and Marco Moretti Sala and Giacomo Ghiringhelli},
howpublished = {arXiv},
year = {2026},
month = jul,
doi = {10.48550/arxiv.2607.15763},
eprint = {2607.15763},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.15763},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Machine-learning test of the single-ion model for dd excitations in cuprates
AU - Maryia Zinouyeva
AU - Leonardo Martinelli
AU - Riccardo Arpaia
AU - Nicholas B. Brookes
AU - Daniele Di Castro
AU - Kurt Kummer
AU - Floriana Lombardi
AU - Giacomo Merzoni
AU - Francesco Rosa
AU - Alessandro Tarasio
AU - Enrico Tassi
AU - Flora Yakhou-Harris
AU - Ezio Puppin
AU - Marco Moretti Sala
AU - Giacomo Ghiringhelli
PY - 2026
DA - 2026/07/17
PB - arXiv
DO - 10.48550/arxiv.2607.15763
UR - https://arxiv.org/abs/2607.15763
AB - We investigate dd excitations in Resonant Inelastic X-ray Scattering spectra of YBa_2Cu_3O_6 and La_2CuO_4 using the local single-ion model. The data are analyzed by conventional global fitting and by a convolutional neural network trained within the same theoretical framework. For YBa_2Cu_3O_6, the excited state energies obtained with the two methods coincide, leading to the xy, 3z^2−r^2, xz/yz sequence for increasing energy. This result validates the use of machine learning tools for the analysis of RIXS spectra dominated by dd excitations. By contrast, for La_2CuO_4, the two methods do not converge to a single solution, revealing the limitations of the single-ion model in describing dd excitations in cuprates and pointing to the role of additional contributions beyond a purely local picture in shaping high-energy excitations.
ER -