Bridging Crystal Structure and Material Properties via Bond-Centric Descriptors

TL;DR

This paper introduces MattKeyBond, a bond-centric database with a new bonding descriptor, BA, to improve interpretability and accuracy of ML models predicting material properties by explicitly incorporating electronic structure information.

Contribution

The paper presents a novel bond-centric database and a new descriptor, BA, to explicitly encode electronic bonding features, enhancing ML model interpretability and performance.

Findings

Enables accurate property predictions with limited data

Provides physically interpretable bonding features

Integrates electronic structure into AI workflows

Abstract

Although chemical bonding is the fundamental mechanistic bridge connecting atomic structure to macroscopic material properties, current data-driven materials science largely treats it as an implicit "black box". Existing machine learning (ML) models rely predominantly on geometric coordinates, forcing them to implicitly relearn complex quantum mechanics from scratch. This lack of intermediate physical features limits model interpretability and generalizability, particularly when training data is scarce. To solve this problem, we introduce MattKeyBond, a bond-centric materials database that explicitly maps the local electronic landscape and bonding interactions of materials. Building on this, we propose Bonding Attractivity (BA), a novel element-specific descriptor that quantifies the intrinsic capability of atoms to form covalent networks. By providing pre-calculated, energy-dimensional bonding descriptors, MattKeyBond transforms the implicit "black box" into physically interpretable features. This strategy relieves ML models from the burden of deducing physical laws from pure geometry, enabling accurate predictions even with limited data and seamlessly integrating electronic structure theory into modern AI workflows.