Combinatorial screening for new materials in unconstrained composition space with machine learning
Combinatorial screening for new materials in unconstrained composition space with machine learning
复制标题
DOI：
10.1103/physrevb.89.094104
复制
发表时间：
2014-03-14
影响因子：
3.7
通讯作者：
Wolverton, C.
中科院分区：
文献类型：
--
作者：
Meredig, B.;Agrawal, A.;Wolverton, C.
通常，为了便于处理，新材料的计算筛选严格限制了成分搜索空间、结构搜索空间或两者。为了解除这些限制，我们从数千个密度泛函理论（DFT）计算的数据库中构建了一个机器学习模型。由此产生的模型可以预测任意组成的热力学稳定性，而无需任何其他输入，并与6个数量级的计算机时间比DFT。我们使用这个模型扫描了大约160万种新的三元化合物（A（x）B（y）C（z））的候选成分，并预测了4500种新的稳定材料。我们的方法可以很容易地应用到其他感兴趣的描述符，以加速特定领域的材料发现。
Typically, computational screens for new materials sharply constrain the compositional search space, structural search space, or both, for the sake of tractability. To lift these constraints, we construct a machine learning model from a database of thousands of density functional theory (DFT) calculations. The resulting model can predict the thermodynamic stability of arbitrary compositions without any other input and with six orders of magnitude less computer time than DFT. We use this model to scan roughly 1.6 million candidate compositions for novel ternary compounds (A(x)B(y)C(z)), and predict 4500 new stable materials. Our method can be readily applied to other descriptors of interest to accelerate domain-specific materials discovery.