Predicting synthesizability of crystalline materials via deep learning
Predicting synthesizability of crystalline materials via deep learning
复制标题
DOI：
10.1038/s43246-021-00219-x
复制
发表时间：
2021-11-18
影响因子：
7.8
通讯作者：
Kadkhodaei, Sara
中科院分区：
文献类型：
--
作者：
Davariashtiyani, Ali;Kadkhodaie, Zahra;Kadkhodaei, Sara
预测未知晶体的可合成性对于加速材料发现非常重要。在这里，任何给定成分和结构的晶体的可合成性都可以通过深度学习模型来预测，该模型将晶体映射到卷积神经网络处理的彩色编码3D图像上。预测假设晶体的可合成性具有挑战性，因为控制材料合成的参数范围很广。然而，为任何未来的应用探索新晶体的指数级大空间需要对合成可能性的准确预测能力，以避免偶然的试错。通常，可合成性的基准是基于晶体结构的能量来定义的。在这里，我们采取了另一种方法来选择的潜在信息嵌入在晶体材料的可合成性的功能。我们通过三维像素图像来表示晶体材料的原子结构，这些图像由其化学属性进行颜色编码。晶体的图像表示使得能够使用卷积编码器来学习隐藏在晶体材料的结构和化学排列中的可合成性特征。基于所提出的模型，我们可以准确地将材料分类为可合成的晶体与晶体异常，这些晶体结构类型和化学成分范围很广。我们通过预测电池电极和热电应用的假想晶体的合成能力来说明该模型的有用性。
Predicting the synthesizability of unknown crystals is important for accelerating materials discovery. Here, the synthesizability of crystals with any given composition and structure can be predicted by a deep learning model that maps crystals onto color-coded 3D images processed by convolutional neural networks.Predicting the synthesizability of hypothetical crystals is challenging because of the wide range of parameters that govern materials synthesis. Yet, exploring the exponentially large space of novel crystals for any future application demands an accurate predictive capability for synthesis likelihood to avoid a haphazard trial-and-error. Typically, benchmarks of synthesizability are defined based on the energy of crystal structures. Here, we take an alternative approach to select features of synthesizability from the latent information embedded in crystalline materials. We represent the atomic structure of crystalline materials by three-dimensional pixel-wise images that are color-coded by their chemical attributes. The image representation of crystals enables the use of a convolutional encoder to learn the features of synthesizability hidden in structural and chemical arrangements of crystalline materials. Based on the presented model, we can accurately classify materials into synthesizable crystals versus crystal anomalies across a broad range of crystal structure types and chemical compositions. We illustrate the usefulness of the model by predicting the synthesizability of hypothetical crystals for battery electrode and thermoelectric applications.