A Padding Method for Enhanced Encoding of Inorganic Structures with Varying Chemical Compositions

2026-05-28

AI Summary

This work addresses the challenges of accuracy and efficiency in generative models for designing inorganic materials with diverse chemical compositions, which arise from structural complexity and vast combinatorial spaces. The authors propose an end-to-end crystal symmetry–aware generation framework that integrates a Wyckoff-position length-aware occupancy strategy with a symmetry-aware deep encoder, further enhanced by machine-learned interatomic potentials for stability filtering. This approach enables more robust and information-rich representations of inorganic crystal structures. Experimental results demonstrate a 5.3% improvement in reconstruction accuracy on a proton conductor dataset and a 63.5% increase in the number of novel, stable materials generated compared to baseline methods on the perov-5 dataset.

Abstract

Designing novel inorganic materials through generative models remains an important challenge for material science, driven by the complexity and diversity of inorganic structures across expansive chemical compositions and structural landscape. The vast combinatorial space of inorganic compounds demands innovative, AI-driven approaches to overcome limitations in generative accuracy and efficiency. To address this, we introduce a novel method that redefines the encoding and generation of inorganic materials by utilizing domain-specific symmetry-aware representation. Our approach not only refines the representation of intricate inorganic structures but also contributes to the field of material discovery by enhancing the precision and stability of generated candidates. Central to our methodology is a novel padding technique that exploits crystal symmetry information to enhance the encoding process. By integrating Wyckoff position length-aware padding into an encoder architecture, we achieve a more robust informed representation of inorganic materials. This symmetry-driven enhancement improves deep learning models to generate stable, previously unexplored inorganic structures with superior accuracy and computational efficiency. Furthermore, we introduce an end-to-end system that leverages the machine learning potential models to seamlessly generate novel, even those unseen in the training data, and stable inorganic materials from initial data to validated output. This pipeline integrates advanced generative models with stability analysis, marking a significant leap forward in the automated exploration and design of next-generation inorganic materials. Our method improved reconstruction accuracy 5.3% in proton conductor data, and generated 63.5% more novel stable inorganic material to baseline model on the perov-5 dataset.

Problem

• inorganic materials
• generative models
• chemical composition
• structural encoding
• material discovery

Innovation

• symmetry-aware representation
• Wyckoff position padding
• inorganic material generation
• end-to-end generative model
• crystal structure encoding