Material representations that are compatible with machine learning models play a key role in developing models that exhibit high accuracy for property prediction. Atomic orbital interactions are one of the important factors that govern the properties of crystalline materials from which the local chemical environments of atoms is inferred. Therefore, to develop robust machine learning models for material properties prediction, it is imperative to include features representing such chemical attributes. Here, we propose the orbital graph convolutional neural network (OGCNN), a crystal graph convolutional neural network framework that includes atomic orbital interaction features that learns material properties in a robust way. In addition, we embedded an encoder-decoder network into the OGCNN enabling it to learn important features among basic atomic (elemental features), orbital-orbital interactions, and topological features. We examined the performance of this model on a broad range of crystalline materials data to predict different properties. We benchmarked the performance of the OGCNN model with that of: (1) the crystal graph convolutional neural network, (2) other state-of-the-art descriptors for material representations including many-body tensor representation and the smooth overlap of atomic positions, and (3) other conventional regression machine learning algorithms where different crystal featurization methods have been used. We find that the OGCNN significantly outperforms them. The OGCNN model with high predictive accuracy can be used to discover new materials among the immense phase and compound spaces of materials.

中文翻译：

---

轨道图卷积神经网络用于材料性能预测

与机器学习模型兼容的材料表示在开发对属性预测显示出高精度的模型中起着关键作用。原子轨道相互作用是决定晶体材料特性的重要因素之一，从中可以推断出原子的局部化学环境。因此，要开发用于材料性能预测的鲁棒机器学习模型，必须包括代表此类化学属性的特征。在这里，我们提出了轨道图卷积神经网络（OGCNN），这是一种晶体图卷积神经网络框架，其中包括原子轨道相互作用特征，可以以可靠的方式学习材料特性。此外，我们将编码器-解码器网络嵌入到OGCNN中，使其能够学习基本原子（基本特征），轨道-轨道相互作用和拓扑特征之间的重要特征。我们在广泛的晶体材料数据上检查了该模型的性能，以预测不同的性能。我们使用以下各项对OGCNN模型的性能进行基准测试：（1）晶体图卷积神经网络；（2）其他用于材料表示的最新描述符，包括多体张量表示和原子位置的平滑重叠（3）其他传统的回归机器学习算法，其中使用了不同的晶体特征化方法。我们发现OGCNN的性能明显优于它们。