Skip to content

An Interpretable and Transferable Physics-Aware Machine-Learning Framework for Stability Prediction of Dual-Atom Alloys

Oct 2026 · Chemistry of Materials · Vol 38, pp. 10950-10961 · 0 citations · 42 references

TL;DR

This work constructs a library of 6804 candidate structures spanning nine crystal planes and two representative dual-atom configurations, providing a generalizable theoretical foundation for the thermodynamic screening and rational design of DAAs with high synthetic feasibility in energy catalysis.

Abstract

Dual-atom alloys (DAAs) embedded in metallic surfaces constitute an emerging catalytic platform fundamentally distinct from the widely studied carbon-supported dual-atom sites, as they enable intrinsic metal–metal cooperation within an active metallic environment. However, a systematic understanding of their structure–stability relationships remains elusive, mainly due to the prohibitive cost of exploring the vast space of compositions, crystal surfaces, and atomic configurations. Here, using Cu-based DAAs as a prototypical platform, we construct a library of 6804 candidate structures spanning nine crystal planes and two representative dual-atom configurations. Density functional theory (DFT)-calculated formation energies for 930 representative structures (13.7% of the library) are employed to train a physics-informed residual multilayer perceptron model combined with 5-fold ensemble learning. The model achieves high predictive accuracy with cross-validation R2 > 0.906 and demonstrates robust transferability across different crystal planes and structural motifs, outperforming conventional machine-learning baselines. Interpretable SHAP analysis indicates that electronic structure descriptors predominantly govern stability, with geometric compatibility contributing as a secondary factor. Systematic stability trends are identified, including a thermodynamic preference for diagonal configurations on the (100), (311), and (411) surfaces, linear-close configurations on the (110), (111), and (211) surfaces, and enhanced stability for noble-metal dopants, such as Au, Pt, and Pd. Electronic structure analysis further establishes a clear correlation between formation energy and the dopant d-band center, with greater stability achieved when the d-band center is located farther from the Fermi level. With the training on a limited number of DFT-calculated samples, this physics-aware and transferable machine-learning framework enables rapid and data-efficient prediction of dual-atom alloy stability. The approach is readily extensible to diverse crystal surfaces and alloy systems, providing a generalizable theoretical foundation for the thermodynamic screening and rational design of DAAs with high synthetic feasibility in energy catalysis.

View source

Similar papers

Preprint Sep 2026

Enabling Domain-Specific Atomistic Models: A Machine Learning Potential for the Solid Acid Family

A potential is presented that is universal within the class of water-free solid-state hydrogen-bond network mediated proton conductors rather than across chemistry and a database of 4.4 million first-principles configurations spanning 55 materials, offering a template for other compound classes.

Jonas Hänseroth, Rose von Stackelberg, C. Dressler · 0 citations
Open access Sep 2026

A Multi‐Scale Machine Learning Framework for the Inverse Design of High Entropy Alloys

High‐entropy alloys (HEAs) are highly promising electrocatalysts, but the vastness of their configurational space severely limits traditional screening approaches. To overcome this challenge, this article proposes a conceptual and methodological paradigm shift toward “Inverse Design” (“property‐to‐material”) by introdu...

Mikael Takoutsin, Marta Campolucci, Nicolas de Andrade Ishiki et al. · 0 citations
Open access Oct 2026

Two-atom interaction potential database supporting physics-informed features for machine learning and material property prediction.

Accurately predicting the energy and relevant properties of molecules and complex crystalline systems remains a cornerstone of computational materials science. While density functional theory (DFT) offers high accuracy, its computational cost scales prohibitively for large-scale materials. In this work, we present a co...

A. Kesorn, Cheewawut Na Talang, A. Sinsarp et al. · 0 citations
Preprint Oct 2026

MOFFieldBench: A Machine Learning Benchmark for Continuous Electronic Fields in Metal-Organic Frameworks

Machine-learning models for metal-organic frameworks (MOFs) predominantly rely on atomic structures, whereas electron-density (ED) and electrostatic-potential (ESP) fields remain underexplored as scalable learning representations. These continuous fields encode complementary spatial and electronic information relevant...

Zhao-Lin Hu, He-He Fan, Chen-Hao Rao et al. · 0 citations
Nov 2026

From Physics-Informed Deep Learning to Experimental Realization: Unlocking Entropy-Stabilized Titanium Halide Solid Electrolytes.

Accelerating the discovery of high-performance solid electrolytes (SEs) is hindered by scarce experimental data and vast inorganic chemical spaces. Here, we present a physics-informed deep learning platform that integrates a physics-informed neural network with a dual-source graph neural network. By embedding fundament...

Zhang-Yi Xu, Yu-Cen Yan, Shu-Qing Nie et al. · 0 citations
Preprint Oct 2026

Equivariant generative diffusion learns and generalizes the structural ensemble of amorphous oxides

Amorphous materials are statistical ensembles rather than definitive structures, and conventional density-functional (DFT) and machine-learned-potential simulations sample only a small part of that ensemble. We present an $SE(3)$-equivariant denoising-diffusion model that learns the configurational distribution of amor...

Jun Jiang, Ian Berry, J. N. Fry et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.