Interpretable Machine Learning of Nanoparticle Stability through Topological Layer Embeddings

TL;DR

This paper presents a data-efficient, interpretable machine learning framework that predicts nanoparticle stability by decomposing structures into surface, intermediate, and core regions, enabling physical insights and accurate configuration ranking.

Contribution

The authors introduce a novel layer-resolved descriptor and a ranking-based learning strategy that together improve stability prediction with limited data and provide physical interpretability.

Findings

High accuracy in identifying stable configurations with few DFT calculations

Layer-weighting and SHAP analyses reveal physical factors influencing stability

Rapid convergence of ranking performance with moderate training data

Abstract

The stability of chemically complex nanoparticles is governed by an immense configurational space arising from heterogeneous local atomic environments across surface and interior regions. Efficiently identifying low-energy configurations within this space remains a central challenge for first-principles-based materials discovery, particularly when the available reference data are limited. Here, we introduce a data-efficient and physically interpretable machine-learning framework based on a fragmented, layer-resolved descriptor that explicitly decomposes nanoparticles into surface, intermediate, and core environments using a topology-driven definition. This representation preserves a compact and fixed feature dimensionality while retaining spatial resolution, enabling controlled emphasis on different regions of the nanoparticle through physically motivated weighting schemes. Coupled with gradient-boosted decision tree models and a ranking-based learning strategy, the proposed framework enables accurate identification of the most stable nanoparticle configurations using only a few hundred density functional theory reference calculations. Ranking performance metrics demonstrate near-saturation of correlation, high top-k recall, and rapidly vanishing regret at moderate training-set sizes, highlighting the strong data efficiency of the approach. Beyond predictive performance, layer-weighting and SHAP-based interpretability analyses reveal how surface segregation, coordination topology, and local chemical disorder contribute differently to stability across spatial regions of the nanoparticle. These insights provide a transparent physical interpretation of the learned models and establish a natural pathway toward active learning-driven exploration of complex nanoparticle configurational spaces.