This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility: Researchers from the Skoltech Materials Center have proposed a new approach to modeling the mechanical properties of heterogeneous materials, combining machine learning with active learning on local chemical configurations. The method enables calculations of large systems containing tens of thousands of atoms with accuracy comparable to direct quantum-mechanical calculations (DFT), but without requiring extensive computational resources.
The study has been published in Computational Materials Science. The methodology is based on moment tensor potentials (MTPs), which are trained on data obtained from density functional theory calculations. During the simulation, the system automatically identifies local atomic environments for which the potentials' energy predictions become unreliable (extrapolative), extracts them from the large simulation cell and sends them for additional DFT calculations.
These fragments are then added to the training set, and the potential is retrained, progressively expanding its domain of applicability. The authors applied this approach to WC‑Co composites—hard alloys based on tungsten carbide, also known as pobedit, widely used in industry because of their high hardness and fracture toughness. The approach, based on active learning on local chemical configurations, enables the modeling of large polycrystalline and composite systems, including defects and grain boundaries that are inaccessible to direct DFT calculations, while maintaining the accuracy of quantum-mechanical description.
The method is applicable to a wide range of heterogeneous materials—from ceramics and metal ceramics to nanostructured composites. "Developing new materials with desired properties requires a detailed understanding of the relationship between structure and mechanical characteristics," said Alexander Kvashnin, the study's principal investigator and a professor at the Skoltech Materials Center. "However, direct modeling of heterogeneous systems using DFT is impossible due to limitations on the number of atoms: These calculations are only applicable to systems of a few hundred atoms, whereas real polycrystalline materials contain tens of thousands of atoms.
"Our proposed approach solves this problem: we automatically collect information about local atomic configurations encountered in the material and use it to train the potential, maintaining DFT accuracy at scales sufficient for modeling industrial composites. This gives engineers and materials scientists a tool for predictive calculation of material properties without costly experiments." "Using WC‑Co as an example, we demonstrated how the method allows for a quantitative description of the transition from brittle to ductile behavior as the cobalt binder content increases. Such data are important for designing materials with an optimal balance of hardness and fracture toughness.
Our approach is universal and can be applied to a wide variety of composite and polycrystalline materials," noted Faridun Jalolov, the first author of the study and a Ph.D. student in the Materials Science and Engineering program at Skoltech. Jalolov et al, Accurate predictions of mechanical properties using active learning on local chemical configurations: A case study of WC–Co composites, Computational Materials Science (2026). DOI: 10.1016/j.commatsci.2026.114962 Provided by Skolkovo Institute of Science and Technology BSc Life Sciences & Ecology.
Extract — continue reading at the source.
