ML-COHP: predicting bond descriptors using latent space of a universal interatomic potentials
Abstract
The integrated crystal orbital Hamilton population (ICOHP) is the standard measure of bond strength in a DFT calculation, but every structure needs its own DFT single point and LOBSTER projection, which takes days for a cell of a hundred atoms, such as a grain boundary or a catalytic nanoparticle. We predict ICOHP from the frozen descriptors of a MACE foundation model. A symmetric pair head reads the scalar and bond-projected vector channels of the two atoms and corrects a pair baseline built from the element embeddings of the same model. We tested the model on the high-entropy diboride (Hf,Zr,Ti,Nb,Ta)B2, Pt clusters on defective graphene and Pt/Pd nanoparticles with adsorbed O2. The error on bonds stronger than 0.5 eV is 1.6-4.1%, about half that of the Gaussian-process model of Ferreira et al. trained on the same data. Trained only on high-temperature HEB2 snapshots, the model reproduces the LOBSTER ICOHP of relaxed grain boundary cells to 0.06 eV in about a second, against 5-51 hours of LOBSTER. The vector channels halve the error compared to the scalar ones, and the baseline keeps the model usable with two training structures. With geometries from a fine-tuned MACE potential, the model gives the bonding of Pt/Pd particles over a continuous O2 coverage, and DFT on these particles shows that O2 costs a Pt-rich shell several times more metal--metal bonding than a Pd shell.
Related
- Can Universal Machine-Learning Interatomic Potentials Capture Small Polarons? A Geometry-Based Benchmark in Transition-Metal Oxides
- Diagnosing Latent Energy Decomposition in Machine-Learning Interatomic Potentials via Interacting Quantum Atoms
- From sparse quantum-computing data to atomistic simulation with universal machine-learning interatomic potentials
- Universal Interatomic Potentials as Configuration-Space Generators for One-Shot and Iterative Fine-Tuning of Ab Initio-Accurate Material-Specific Models
- Understanding compression-extension error asymmetry in universal machine-learning interatomic potentials
BibTeX
@misc{alekseev2026mlcohp,
title = {{ML-COHP: predicting bond descriptors using latent space of a universal interatomic potentials}},
author = {Daniil S. Alekseev and Ilya V. Chepkasov and Alexander G. Kvashnin},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.40445},
eprint = {2610.40445},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.40445},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - ML-COHP: predicting bond descriptors using latent space of a universal interatomic potentials
AU - Daniil S. Alekseev
AU - Ilya V. Chepkasov
AU - Alexander G. Kvashnin
PY - 2026
DA - 2026/10/29
PB - arXiv
DO - 10.48550/arxiv.2610.40445
UR - https://arxiv.org/abs/2610.40445
AB - The integrated crystal orbital Hamilton population (ICOHP) is the standard measure of bond strength in a DFT calculation, but every structure needs its own DFT single point and LOBSTER projection, which takes days for a cell of a hundred atoms, such as a grain boundary or a catalytic nanoparticle. We predict ICOHP from the frozen descriptors of a MACE foundation model. A symmetric pair head reads the scalar and bond-projected vector channels of the two atoms and corrects a pair baseline built from the element embeddings of the same model. We tested the model on the high-entropy diboride (Hf,Zr,Ti,Nb,Ta)B_2, Pt clusters on defective graphene and Pt/Pd nanoparticles with adsorbed O_2. The error on bonds stronger than 0.5 eV is 1.6-4.1%, about half that of the Gaussian-process model of Ferreira et al. trained on the same data. Trained only on high-temperature HEB_2 snapshots, the model reproduces the LOBSTER ICOHP of relaxed grain boundary cells to 0.06 eV in about a second, against 5-51 hours of LOBSTER. The vector channels halve the error compared to the scalar ones, and the baseline keeps the model usable with two training structures. With geometries from a fine-tuned MACE potential, the model gives the bonding of Pt/Pd particles over a continuous O_2 coverage, and DFT on these particles shows that O_2 costs a Pt-rich shell several times more metal--metal bonding than a Pd shell.
ER -