Machine learning material properties from the periodic table using convolutional neural networks†,Chemical Science

当前位置： X-MOL 学术 › Chem. Sci. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Machine learning material properties from the periodic table using convolutional neural networks†
Chemical Science ( IF 7.6 ) Pub Date : 2018-09-12 00:00:00 , DOI: 10.1039/c8sc02648c
Xiaolong Zheng _{1,

2,

3,

4} , Peng Zheng _{1,

2,

3,

4} , Rui-Zhi Zhang _{4,

5,

6,

7}

Affiliation

In recent years, convolutional neural networks (CNNs) have achieved great success in image recognition and shown powerful feature extraction ability. Here we show that CNNs can learn the inner structure and chemical information in the periodic table. Using the periodic table as representation, and full-Heusler compounds in the Open Quantum Materials Database (OQMD) as training and test samples, a multi-task CNN was trained to output the lattice parameter and enthalpy of formation simultaneously. The mean prediction errors were within DFT precision, and the results were much better than those obtained using only Mendeleev numbers or a random-element-positioning table, indicating that the two-dimensional inner structure of the periodic table was learned by the CNN as useful chemical information. Transfer learning was then utilized by fine-tuning the weights previously initialized on the OQMD training set. Using compounds with formula X₂YZ in the Inorganic Crystal Structure Database (ICSD) as a second training set, the stability of full-Heusler compounds was predicted by using the fine-tuned CNN, and tungsten containing compounds were identified as rarely reported but potentially stable compounds.

中文翻译：

使用卷积神经网络从元素周期表中机器学习材料的特性†

近年来，卷积神经网络（CNN）在图像识别方面取得了巨大成功，并表现出强大的特征提取能力。在这里，我们表明CNN可以学习元素周期表中的内部结构和化学信息。使用元素周期表作为表示形式，并使用开放量子材料数据库（OQMD）中的全Heusler化合物作为训练和测试样本，训练了多任务CNN以同时输出晶格参数和形成焓。平均预测误差在DFT精度范围内，并且其结果比仅使用门捷列夫数或随机元素定位表获得的结果要好得多，这表明CNN知道周期表的二维内部结构是有用的化学信息。然后，通过微调先前在OQMD训练集上初始化的权重来利用转移学习。使用具有化学式X的化合物无机晶体结构数据库（ICSD）中的₂ YZ作为第二个训练集，通过使用微调的CNN可以预测全Heusler化合物的稳定性，而含钨化合物则被确定为鲜有报道但可能稳定的化合物。

更新日期：2018-09-12

点击分享查看原文

点击收藏

公开下载

阅读更多本刊最新论文本刊介绍/投稿指南11