From Heuristics to Machine Learning: The Performance Ceiling for Single-Ion Magnets and Its Electronic Origin
Abstract
Machine learning (ML) is expected to speed up the discovery of single-ion magnets (SIMs), but does the structural information available before synthesis allow such predictions? For 1215 lanthanide complexes from the SIMDAVIS 1.2.1 database we compared three increasing levels of structural description: tabular features of the coordination site, continuous symmetry measures of the coordination polyhedron, and the complete 3D arrangement of atoms. All three converge to an accuracy near 76%, only slightly above the 71% of the single rule "predict SIM for Dy3+". To explain the failures, we combined multireference ab initio calculations with an inspection of the structures behind the high-confidence errors. The SIMs missed by the geometric models are field-induced relaxers whose ground Kramers doublets are prone to tunnelling, a property invisible to geometric descriptors. Many false positives contain several lanthanide centers or radicals, so their relaxation is collective and outside the single-ion picture. The electronic-structure and connectivity information needed to identify SIMs is therefore not accessible to geometric methods alone. Geometric models remain useful: restricting the screening to compounds with high prediction confidence raises the accuracy to 88% while retaining 48% of the dataset. Building on the analysis of the failures, we propose a strategy that combines simple filters for nuclearity and for radicals with ligand-field descriptors from ab initio calculations.
Related
- Electronic configuration vectors provide transferable elemental representations for machine learning across the periodic table
- Machine-Learning-Guided Prediction and Statistical Analysis of Electronic Bandgaps in Double-Perovskite Oxides for Photovoltaic and Optoelectronic Design
- Electronic-Structure-Informed Many-Body Encoding for Quantum Machine Learning
- Machine Learning-Assisted Analysis of Chloride-Enhanced BiOCl/DSA Anode for Synergistic Denitrification and Tetracycline Degradation: Performance, Mechanisms, and Product Regulation
- Machine-learning prediction of optical band gaps and photocatalytic performance in rare-earth-doped spinel ferrites
BibTeX
@misc{zahariev2026from,
title = {{From Heuristics to Machine Learning: The Performance Ceiling for Single-Ion Magnets and Its Electronic Origin}},
author = {Federico Zahariev and Regina Pereyra and Vassiliki-Alexandra Glezakou and Durga Paudyal},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.24038},
eprint = {2609.24038},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.24038},
}
RIS
TY - UNPB
TI - From Heuristics to Machine Learning: The Performance Ceiling for Single-Ion Magnets and Its Electronic Origin
AU - Federico Zahariev
AU - Regina Pereyra
AU - Vassiliki-Alexandra Glezakou
AU - Durga Paudyal
PY - 2026
DA - 2026/09/21
PB - arXiv
DO - 10.48550/arxiv.2609.24038
UR - https://arxiv.org/abs/2609.24038
AB - Machine learning (ML) is expected to speed up the discovery of single-ion magnets (SIMs), but does the structural information available before synthesis allow such predictions? For 1215 lanthanide complexes from the SIMDAVIS 1.2.1 database we compared three increasing levels of structural description: tabular features of the coordination site, continuous symmetry measures of the coordination polyhedron, and the complete 3D arrangement of atoms. All three converge to an accuracy near 76%, only slightly above the 71% of the single rule "predict SIM for Dy3+". To explain the failures, we combined multireference ab initio calculations with an inspection of the structures behind the high-confidence errors. The SIMs missed by the geometric models are field-induced relaxers whose ground Kramers doublets are prone to tunnelling, a property invisible to geometric descriptors. Many false positives contain several lanthanide centers or radicals, so their relaxation is collective and outside the single-ion picture. The electronic-structure and connectivity information needed to identify SIMs is therefore not accessible to geometric methods alone. Geometric models remain useful: restricting the screening to compounds with high prediction confidence raises the accuracy to 88% while retaining 48% of the dataset. Building on the analysis of the failures, we propose a strategy that combines simple filters for nuclearity and for radicals with ligand-field descriptors from ab initio calculations.
ER -