arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.05204cond-mat.mtrl-sci
收藏

利用持久同调特征通过图神经网络实现缺陷形成能的精准预测

Leveraging Persistent Homology Features for Accurate Defect Formation Energy Predictions via Graph Neural Networks

Zhenyao Fang, Qimin Yan

AI总结:

针对现有图神经网络预测缺陷性质精度受限的问题,本研究引入持久同调特征表征缺陷结构信息,结合图池化操作大幅提升预测精度,可普适优化多种前沿GNN模型,还能解决超胞收敛问题并准确预测缺陷相互作用。

摘要:

在机器学习辅助的高通量缺陷研究中,超胞结构的缺陷感知隐表示对准确预测缺陷性质至关重要。由于缺陷性质强烈依赖于缺陷位点附近的局域原子构型,且图神经网络(GNN)存在过平滑问题,现有GNN模型的性能受到限制。本文证明,编码每个原子位点周围局域化学环境拓扑信息的持久同调特征能够表征缺陷的结构信息。以包含各类氧基钙钛矿及其所有可能空位的数据集为例,研究表明引入持久同调特征并合理选择图池化操作,可显著提升预测精度,平均绝对误差(MAE)降低55%。这些特征可轻松集成到图Transformer网络、等变神经网络等前沿GNN模型中,并普遍提升其性能。此外,本文模型还解决了以往GNN模型存在的超胞尺寸收敛问题。进一步地,以含多种取代和多种空位的缺陷BaTiO₃数据集为例,本文的GNN模型还能准确预测缺陷-缺陷相互作用。这些结果表明,持久同调特征可有效提升机器学习模型性能,助力加速发现面向技术应用的功能型缺陷。

英文摘要:

In machine-learning-assisted high-throughput defect studies, a defect-aware latent representation of the supercell structure is crucial to the accurate prediction of defect properties. The performance of current graph neural network (GNN) models is limited due to the fact that defect properties depend strongly on the local atomic configurations near the defect sites and due to the over-smoothing problem of GNN. Herein, we demonstrate that persistent homology features, which encode the topological information of local chemical environment around each atomic site, can characterize the structural information of defects. Using the dataset containing a wide spectrum of \ch{O}-based perovskites with all available vacancies as an example, we show that incorporating the persistent homology features, along with proper choices of graph pooling operations, significantly increases the prediction accuracy, with the MAE reduced by 55\%. Those features can be easily integrated into the state-of-the-art GNN models, including the graph Transformer network and the equivariant neural network, and universally improve their performance. Besides, our model also overcomes the convergence issue with respect to the supercell size that was present in previous GNN models. Furthermore, using the datasets of defective \ch{BaTiO3} with multiple substitutions and multiple vacancies as examples, our GNN model can also predict the defect-defect interactions accurately. These results suggest that persistent homology features can effectively improve the performance of machine learning models and assist the accelerated discovery of functional defects for technological applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑