This work demonstrates that the PASS method yields an accurate and transferable MLIP which is capable of capturing the reactive complexity of oxide growth while remaining computationally practical for extended systems.
Abstract
Accurate atomistic modelling of iron (Fe) oxidation requires a reliable interatomic potential, which necessitates an extensive and representative first-principles dataset for training the interatomic potential. However, Fe-oxygen (O) system is known for its structural and magnetic complexity, rendering the generation of high-quality dataset challenging. In this work, we propose the Perturbation Augmented Space group structure Sampling (PASS) method to generate extensive and representative dataset consisting of small-cell structures with less than 10 atoms. We present a systematic approach to developing a first of its kind transferable machine learning interatomic potential (MLIP) for Fe-O system based on the atomic cluster expansion (ACE) framework. We thoroughly validate the accuracy and capability of the ACE MLIP across both pure Fe and Fe-O systems through bulk, surface, and interface properties. We showcase the formation of FeO-like structure in large-scale Fe oxidation simulation using the ACE MLIP. This work demonstrates that the PASS method yields an accurate and transferable MLIP which is capable of capturing the reactive complexity of oxide growth while remaining computationally practical for extended systems.
Foundation machine-learning interatomic potentials (MLIPs) enable atomistic simulations at substantially lower computational cost than first-principles methods, but their reliability across structural geometries remains insufficiently understood. Here, we construct a density-functional-theory dataset of ZrO2 configurations spanning bulk, slab, particle, neck, and atomically thin wire environments motivated by an experimentally observed ZrO2 desintering process involving neck thinning and atomic wire formation. We first benchmark 26 pretrained MLIPs and observe pronounced geometry-dependent degradation in zero-shot predictions. Without any training, after only reference-energy alignment, the best zero-shot model (ORB-V3) reaches energy and force root-mean-square errors of 6 meV/atom and 197.3 meV/{\AA}, respectively, with the largest force errors in neck and wire configurations. We then compare zero-shot inference, fine-tuning, and training from scratch strategies. Fine-tuning yields lower energy and force errors than training from scratch, while both require comparable wall-clock time. Geometry-specific fine-tuning improves in-domain accuracy but frequently produces negative transfer to other structural classes, whereas mixed-geometry fine-tuning reduces cross-geometry errors. Evaluations of elastic and vibrational properties, surface energies, and neck dynamics further show that rankings based on average energy and force errors do not universally predict property-level behavior. These results demonstrate that geometry-diverse target data and independent physical validations are necessary when adapting foundation MLIPs to low-coordination (ionic) nanostructures.
P. Zanineli, B. Focassio, G. R. Schleder· 0 citations
The Active Learning Framework (ALF), an open-source Python package designed to streamline the design and deployment of MLIP training datasets on High Performance Computing resources, is introduced, illustrating ALF’s effectiveness in compiling datasets that capture essential chemical and structural regimes.
V. Grizzi, P. Lohr, Nikita Fedik et al.· Journal of Chemical Theory a...· 0 citations
Pretrained machine-learning interatomic potentials, so-called universal or foundation models offer an appealing starting point for atomistic simulations, but their accuracy for material-specific observables often remains limited without additional reference data (fine-tuning). Here, we systematically quantify how much first-principles data are required to convert universal models into ab initio-accurate material-specific potentials, and ask whether fine-tuning is necessarily preferable to training from scratch. We compare five universal MLIP frameworks, MACE-MP-0, SevenNet-0, GRACE-1L-OAM, MatterSim-v1-5M and ORB-v2, across seven chemically diverse systems incorporating rare and reactive events. Fine-tuning on only 10 AIMD-derived configurations is insufficient for the investigated systems; 200 configurations succeed in favorable cases, but the outcome remains strongly system-dependent. By contrast, 2000 AIMD configurations constitute a robust default, yielding low force and energy errors and reproducing the target material-specific observables. Moderately dense sub-sampling of the AIMD trajectory reduces the required trajectory length tenfold with little loss in model quality. Training from scratch on the same datasets is competitive with, and often slightly more accurate than, naive fine-tuning for MACE and SevenNet, whereas GRACE requires more data. The energy profile for a sulfur-vacancy jump in MoS$_2$ reveals that low trajectory-level errors do not guarantee a correct reaction profile, highlighting the need for observable-level validation. Finally, we show that averaging independently trained models improves predictions in scarce-data regimes at no additional first-principles cost. Together, these results provide practical guidelines for converting limited AIMD reference data into reliable material-specific MLIPs for nanosecond-timescale simulations at near-DFT accuracy.
This paper introduces a distance measure that assesses the output of material generative models by capturing both quality and novelty in a single distribution-based evaluation framework, and introduces the Coarse-Fine Transport Distance (CFTD), which is used as guidance for a material generative model.
P. Hagemann, Katharina Ueltzen, Simon Müller et al.· 0 citations
A notably simple procedure, a method the authors refer to as deletions, yields superior performance over an array of alternative extraction methods for extracting atomic environments from large, bulk configurations and embedding them into smaller configurations suitable for DFT calculations with periodic boundary conditions.
Jared Stimac, Fei Zhou, Kyle Bushick et al.· 0 citations
Foundation machine learning interatomic potentials (MLIPs) deliver near-ab-initio accuracy at a fraction of the computational cost, yet their promise for Metal-organic Frameworks (MOFs) remains largely unrealized as large unit cells make first-principles training data expensive to generate, fine-tuned models are scarce, and experimentally grounded benchmarks are scarcer still. We introduce uMOF, a three-part contribution addressing this gap. First, we release the largest and most accurate density functional theory dataset for MOFs to date, computed at the r$^2$SCAN-D4 level of theory across 85524 configurations spanning 19950 unique frameworks and 79 elements, covering empty and gas-loaded structures, geometry optimizations, equations of state, and finite-temperature molecular dynamics. Second, we release a literature-mined benchmark of 3986 verified property values (3146 experimental) extracted from 626 papers by a seven-stage, checkpointed multi-pass large language model pipeline, linked to more than 650 crystallographic information files. Third, we release two universal MLIPs for MOFs, uMOF-MH and uMOF-POLAR, fine-tuned from two architecturally distinct MACE foundation models on the uMOF dataset. On near-equilibrium, ``Tier-1''properties (bulk modulus, phonon-derived heat capacity) the uMOF models perform comparably to existing foundation and fine-tuned baselines. On harder, dynamics-sensitive properties like gas adsorption enthalpies via Widom insertion and adsorption isotherms, the uMOF models outperform every baseline we test, including MOF-specialized gas-capture models trained on datasets up to three orders of magnitude larger, cutting error by more than 80% to within experimental uncertainty. We trace this advantage to the physical diversity of the training data and to level of theory where a small (1.7%) fraction of MD simulations is decisive for MLIP stability.
T. J. Inizan, Prathami Divakar Kamath, A. Elena et al.· 0 citations
