Materials representation plays a key role in machine learning based prediction of materials properties and new materials discovery. Currently both graph and 3D voxel representation methods are based on the heterogeneous elements of the crystal structures. Here, we propose to use electronic charge density (ECD) as a generic unified 3D descriptor for materials property prediction with the advantage of possessing close relation with the physical and chemical properties of materials. We developed an ECD based 3D convolutional neural networks (CNNs) for predicting elastic properties of materials, in which CNNs can learn effective hierarchical features with multiple convolving and pooling operations. Extensive benchmark experiments over 2,170 Fm-3m face-centered-cubic (FCC) materials show that our ECD based CNNs can achieve good performance for elasticity prediction. Especially, our CNN models based on the fusion of elemental Magpie features and ECD descriptors achieved the best 5-fold cross-validation performance. More importantly, we showed that our ECD based CNN models can achieve significantly better extrapolation performance when evaluated over non-redundant datasets where there are few neighbor training samples around test samples. As additional validation, we evaluated the predictive performance of our models on 329 materials of space group Fm-3m by comparing to DFT calculated values, which shows better prediction power of our model for bulk modulus than shear modulus. Due to the unified representation power of ECD, it is expected that our ECD based CNN approach can also be applied to predict other physical and chemical properties of crystalline materials.

中文翻译：

---

使用 3D 深度卷积神经网络根据电子电荷密度预测材料的弹性特性

材料表示在基于机器学习的材料特性预测和新材料发现中起着关键作用。目前，图形和 3D 体素表示方法都基于晶体结构的异质元素。在这里，我们建议使用电子电荷密度 (ECD) 作为通用的统一 3D 描述符来进行材料性能预测，其优点是与材料的物理和化学性能密切相关。我们开发了基于 ECD 的 3D 卷积神经网络 (CNN) 来预测材料的弹性特性，其中 CNN 可以通过多个卷积和池化操作学习有效的分层特征。超过 2 的广泛基准实验，170 Fm-3m 面心立方 (FCC) 材料表明，我们基于 ECD 的 CNN 可以实现良好的弹性预测性能。特别是，我们基于元素喜鹊特征和 ECD 描述符融合的 CNN 模型实现了最佳的 5 倍交叉验证性能。更重要的是，我们展示了我们基于 ECD 的 CNN 模型在对非冗余数据集进行评估时可以实现显着更好的外推性能，其中测试样本周围的邻居训练样本很少。作为额外的验证，我们通过与 DFT 计算值进行比较来评估我们的模型对 Fm-3m 空间群的 329 种材料的预测性能，这表明我们的模型对体积模量的预测能力比剪切模量更好。由于ECD的统一代表权，