Assessing the Transferability of General-Purpose MachineLearning Interatomic Potentials for Heterogeneous Catalysis with HetCat26
Abstract
Foundation machine learning interatomic potentials (MLIPs) promise near-density functional theory (DFT) accuracy across broad areas of chemistry and materials science. However, their performance in describing systems and processes relevant to heterogeneous catalysis remains underexplored. Here, we introduce HetCat26, a collection of benchmark tests designed to assess pre-trained MLIPs across key aspects of catalytic modeling, including surface energetics, metal-metal oxide interactions, adsorption, and catalytic reaction networks. Evaluating fifteen foundation models, we find that performance on existing general materials benchmarks is only weakly predictive of performance on HetCat26; transferability to heterogeneous catalysis cannot be inferred from these general benchmarks. Across the benchmark tests, current models describe surface energetics and, perhaps surprisingly, reaction barriers well, whereas larger errors are observed for adsorption, and DFT site preferences are often not reproduced. Two models, eSEN-30M-OAM and MACE-MH-1-OMAT, nevertheless achieve high accuracy across the properties evaluated. Beyond model benchmarking, HetCat26 highlights the importance of training data consistency: PBE and PBE+U calculations should not be mixed within a training set. Overall, we identify challenges limiting the transferability of current foundation MLIPs to heterogeneous catalysis and, more broadly, to chemical reactions at interfaces, providing guidance for the development of the next generation of foundation models.
Related
- Benchmarking machine-learning interatomic potentials using classical force fields
- Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials
- MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials
- Cluster-based Structural Similarity for Dataset Visualization and Data Selection for Machine Learning Interatomic Potentials
- BranchIP: Learning Adaptive Equivariant Computation for Interatomic Potentials
BibTeX
@misc{peuch2026assessing,
title = {{Assessing the Transferability of General-Purpose MachineLearning Interatomic Potentials for Heterogeneous Catalysis with HetCat26}},
author = {Alexandre Peuch and Giaan Kler-Young and Kaifeng Niu and Jinwoo Hwang and Manos Mavrikakis and Angelos Michaelides and Fabian Berger},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.30621},
eprint = {2609.30621},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.30621},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Assessing the Transferability of General-Purpose MachineLearning Interatomic Potentials for Heterogeneous Catalysis with HetCat26
AU - Alexandre Peuch
AU - Giaan Kler-Young
AU - Kaifeng Niu
AU - Jinwoo Hwang
AU - Manos Mavrikakis
AU - Angelos Michaelides
AU - Fabian Berger
PY - 2026
DA - 2026/09/24
PB - arXiv
DO - 10.48550/arxiv.2609.30621
UR - https://arxiv.org/abs/2609.30621
AB - Foundation machine learning interatomic potentials (MLIPs) promise near-density functional theory (DFT) accuracy across broad areas of chemistry and materials science. However, their performance in describing systems and processes relevant to heterogeneous catalysis remains underexplored. Here, we introduce HetCat26, a collection of benchmark tests designed to assess pre-trained MLIPs across key aspects of catalytic modeling, including surface energetics, metal-metal oxide interactions, adsorption, and catalytic reaction networks. Evaluating fifteen foundation models, we find that performance on existing general materials benchmarks is only weakly predictive of performance on HetCat26; transferability to heterogeneous catalysis cannot be inferred from these general benchmarks. Across the benchmark tests, current models describe surface energetics and, perhaps surprisingly, reaction barriers well, whereas larger errors are observed for adsorption, and DFT site preferences are often not reproduced. Two models, eSEN-30M-OAM and MACE-MH-1-OMAT, nevertheless achieve high accuracy across the properties evaluated. Beyond model benchmarking, HetCat26 highlights the importance of training data consistency: PBE and PBE+U calculations should not be mixed within a training set. Overall, we identify challenges limiting the transferability of current foundation MLIPs to heterogeneous catalysis and, more broadly, to chemical reactions at interfaces, providing guidance for the development of the next generation of foundation models.
ER -