ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition
ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition
复制标题
DOI：
10.1038/s41598-018-35934-y
复制
发表时间：
2018-12-04
影响因子：
4.6
通讯作者：
Agrawal, Ankit
中科院分区：
文献类型：
--
作者：
Jha, Dipendra;Ward, Logan;Agrawal, Ankit
用于从元素组成预测材料性质的传统机器学习方法强调了在设计模型输入时利用领域知识的重要性。在这里，我们证明了通过使用深度学习方法，即使只有几千个训练样本，我们也可以绕过这种需要领域知识的手动特征工程，并获得更好的结果。我们提出了一个被称为ElemNet的深度神经网络模型的设计和实现;它使用人工智能自动捕获不同元素之间的物理和化学相互作用以及相似性，从而使其能够以更高的准确性和速度预测材料特性。ElemNet的速度和一流的准确性使我们能够在巨大的组合空间中对新材料候选物进行快速和强大的筛选;在那里我们预测了数十万个可能包含尚未发现的化合物的化学系统。
Conventional machine learning approaches for predicting material properties from elemental compositions have emphasized the importance of leveraging domain knowledge when designing model inputs. Here, we demonstrate that by using a deep learning approach, we can bypass such manual feature engineering requiring domain knowledge and achieve much better results, even with only a few thousand training samples. We present the design and implementation of a deep neural network model referred to as ElemNet; it automatically captures the physical and chemical interactions and similarities between different elements using artificial intelligence which allows it to predict the materials properties with better accuracy and speed. The speed and best-in-class accuracy of ElemNet enable us to perform a fast and robust screening for new material candidates in a huge combinatorial space; where we predict hundreds of thousands of chemical systems that could contain yet-undiscovered compounds.