用坐标编码的图神经网络，高效预测晶体热椭球参数。
A Cartesian Encoding Graph Neural Network for Crystal Structures Property Prediction: Application to Thermal Ellipsoid Estimation
- 将原子几何与温度信息转为笛卡尔坐标输入图网络
- 在20万+晶体数据上实现ADP预测准确率提升10.87%
- 适合材料计算、晶体学研究者快速估算热振动特性
在基于衍射的晶体结构分析中，热椭球由各向异性位移参数（ADPs）表征，反映原子振动及热力学性质，但传统计算成本高昂。本文提出CartNet，一种新型图神经网络，通过将原子几何和晶体温度编码为笛卡尔坐标，实现高效晶体性质预测。该模型引入邻域均衡化技术强化共价与接触相互作用，并采用基于Cholesky分解的输出头确保预测的ADP矩阵有效性。训练时采用SO(3)旋转数据增强策略以应对未见取向。基于剑桥结构数据库（CSD）构建了包含超过20万组实验晶体结构的ADP数据集进行验证。结果表明，CartNet显著降低计算成本，在ADP预测上比现有方法提升10.87%，较理论方法提高34.77%。进一步在形成能、带隙、总能量、凸包上方能量、体模量和剪切模量等任务上测试，于Jarvis数据集提升7.71%，在Materials Project数据集上提升13.16%。这些成果确立了CartNet在多种晶体性质预测中的先进地位。
原文摘要 · Abstract (English)
In diffraction-based crystal structure analysis, thermal ellipsoids, quantified via Anisotropic Displacement Parameters (ADPs), are critical yet challenging to determine. ADPs capture atomic vibrations, reflecting thermal and structural properties, but traditional computation is often expensive. This paper introduces CartNet, a novel graph neural network (GNN) for efficiently predicting crystal properties by encoding atomic geometry into Cartesian coordinates alongside the crystal temperature. CartNet integrates a neighbour equalization technique to emphasize covalent and contact interactions, and a Cholesky-based head to ensure valid ADP predictions. We also propose a rotational SO(3) data augmentation strategy during training to handle unseen orientations. An ADP dataset with over 200,000 experimental crystal structures from the Cambridge Structural Database (CSD) was curated to validate the approach. CartNet significantly reduces computational costs and outperforms existing methods in ADP prediction by 10.87%, while delivering a 34.77% improvement over theoretical approaches. We further evaluated CartNet on other datasets covering formation energy, band gap, total energy, energy above the convex hull, bulk moduli, and shear moduli, achieving 7.71% better results on the Jarvis Dataset and 13.16% on the Materials Project Dataset. These gains establish CartNet as a state-of-the-art solution for diverse crystal property predictions. Project website and online demo: https://www.ee.ub.edu/cartnet
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。