Hereditary Effective Atom Theory for Large-Scale Atomic Structure Prediction
Abstract
Predicting the atomic structure of large systems requires simultaneous exploration of atomic positions, species, and, generally, the number of atoms. The combinatorial growth of possible arrangements can make this search difficult even for standard genetic algorithms. We introduce Hereditary Effective Atom Theory (HEAT), which integrates Effective Atom Theory into a genetic algorithm to enable efficient global search through a differentiable effective-atom representation. Central to the method is a crossover scheme that directly superimposes two parent structures and relaxes the combined structure. HEAT outperforms conventional genetic-algorithm baselines in recovering a missing 240-atom H sublattice, predicting a 364-atom edge-dislocation core, and reconstructing twisted-bilayer WSe2 containing 1150 atoms from ptychographic constraints. These results demonstrate how continuous effective-atom relaxation improves the exploration of large combinatorial structure spaces.
Related
- AI-EXAFS: Physics-Informed Prediction of EXAFS from Atomic Structure.
- Effective Conservation and Bistability of Atomic Alignment under Strong Spin~Exchange
- Temperature-induced effective topology in many-body ultracold atomic quantum systems
- Response of the near-threshold resonances of the dtμ molecular ion to an effective atomic 2s--2p splitting
- Accurate Atomic Correlation Energies and Virial Trends for Correlation-Consistent Effective Core Potentials III: Quantitative Separation of Fixed-Node Biases and Localization Errors in Cs-Rn
BibTeX
@misc{tahmassebpur2026hereditary,
title = {{Hereditary Effective Atom Theory for Large-Scale Atomic Structure Prediction}},
author = {Justin Tahmassebpur and Chia-Hao Lee and Cristobál Méndez and Shake Karapetyan and Schuyler Z. Shi and David A. Muller and Tomás Arias},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.28996},
eprint = {2610.28996},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.28996},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Hereditary Effective Atom Theory for Large-Scale Atomic Structure Prediction
AU - Justin Tahmassebpur
AU - Chia-Hao Lee
AU - Cristobál Méndez
AU - Shake Karapetyan
AU - Schuyler Z. Shi
AU - David A. Muller
AU - Tomás Arias
PY - 2026
DA - 2026/10/20
PB - arXiv
DO - 10.48550/arxiv.2610.28996
UR - https://arxiv.org/abs/2610.28996
AB - Predicting the atomic structure of large systems requires simultaneous exploration of atomic positions, species, and, generally, the number of atoms. The combinatorial growth of possible arrangements can make this search difficult even for standard genetic algorithms. We introduce Hereditary Effective Atom Theory (HEAT), which integrates Effective Atom Theory into a genetic algorithm to enable efficient global search through a differentiable effective-atom representation. Central to the method is a crossover scheme that directly superimposes two parent structures and relaxes the combined structure. HEAT outperforms conventional genetic-algorithm baselines in recovering a missing 240-atom H sublattice, predicting a 364-atom edge-dislocation core, and reconstructing twisted-bilayer WSe_2 containing 1150 atoms from ptychographic constraints. These results demonstrate how continuous effective-atom relaxation improves the exploration of large combinatorial structure spaces.
ER -