An Ontology for Machine Learning Interatomic Potentials

2026-07-25

AI Summary

This study addresses the lack of standardized metadata in machine learning interatomic potentials (MLIPs), which hinders reproducibility and cross-study comparability. To resolve this, the work proposes the first modular OWL 2 DL ontology for the MLIP domain, integrating existing ontologies such as MDO, CMSO/ASMO, and ML-Schema. The ontology employs formal axioms and property chains to semantically link models, training data (including DFT provenance), hyperparameters, and benchmarking protocols, ensuring semantic consistency and enabling automated reasoning. Evaluated on a knowledge graph constructed from 20 published studies, the ontology demonstrates its capacity to answer competency questions, support logical inference, and significantly enhance the reproducibility and interoperability of MLIP research.

Abstract

Machine learning interatomic potentials (MLIPs) approximate quantum-mechanical energies and forces---conventionally computed by density functional theory (DFT) or wave-function methods---at a fraction of the cost. The field encompasses a growing ecosystem of algorithms, training datasets, hyperparameters, and target materials, yet the metadata needed to systematically compare, reproduce, and build upon MLIP studies remains scattered across papers, scripts, and ad-hoc file formats. We present the MLIPs ontology, an OWL 2 DL ontology that captures the concepts needed to describe MLIP methods, their hyperparameters, training datasets with DFT provenance, and published benchmarks. The ontology is organized into three modules---Method, Training Data, and Benchmark---and connects existing ontologies in materials science (MDO, CMSO/ASMO) and machine learning (ML-Schema), complementing dataset-side schemas such as Croissant. It declares 27 formal axioms enforcing data completeness and consistency, including property chains that link trained models to their methods and training data. We demonstrate the ontology through a running example based on Moment Tensor Potentials and evaluate it through competency-question execution on a 20-paper seeded knowledge graph, OWL reasoning, and comparison with existing ontologies.

Problem

• machine learning interatomic potentials
• ontology
• metadata
• reproducibility
• materials science

Innovation

• ontology
• machine learning interatomic potentials
• OWL 2 DL
• metadata standardization
• knowledge graph