Using machine learning to predict and design materials is an important mean of accelerating material development.One way to improve the accuracy of machine learning predictions is to introduce material structures as d...Using machine learning to predict and design materials is an important mean of accelerating material development.One way to improve the accuracy of machine learning predictions is to introduce material structures as descriptors.However,thecomplexity ofcomputing material structures limits the practical use of these models.To address this challenge and improve prediction accuracy in small data sets,we develop a generative network framework:Elemental Features enhanced and Transferring corrected data augmentation in Generative Adversarial Networks(EFTGAN).Combining the elemental convolution technique with Generative Adversarial Networks(GAN),EFTGAN provides a robust and efficient approach for generating data containing elemental and structural information that can be used not only for data augmentation to improve model accuracy,but also for prediction when the structures are unknown.Applying this framework to the FeNiCoCrMn/Pd high-entropy alloys,we successfully improve the prediction accuracy in a small data set and predict the concentrationdependent formation energies,lattices,and magnetic moments in quinary systems.This study provides a new algorithm to improve the performance and usability of deep learning with structures as inputs,which is effective and accurate for the prediction and development of materials for small data sets.展开更多
基金supported by the National Natural Science Foundation ofChina(grant no.92270104)partially by Grant-in-Aids for Scientific Research on innovative Areas on High Entropy Alloys through the grant number P18H05454 of JSPS,Japan.Authors acknowledge the Center of High Performance Computing,Tsinghua University and the Center for Computational Materials Science of the Institute for Materials Research,Tohoku University for the support of the supercomputing facilities.Figure 1 is drawn by FigDraw.
文摘Using machine learning to predict and design materials is an important mean of accelerating material development.One way to improve the accuracy of machine learning predictions is to introduce material structures as descriptors.However,thecomplexity ofcomputing material structures limits the practical use of these models.To address this challenge and improve prediction accuracy in small data sets,we develop a generative network framework:Elemental Features enhanced and Transferring corrected data augmentation in Generative Adversarial Networks(EFTGAN).Combining the elemental convolution technique with Generative Adversarial Networks(GAN),EFTGAN provides a robust and efficient approach for generating data containing elemental and structural information that can be used not only for data augmentation to improve model accuracy,but also for prediction when the structures are unknown.Applying this framework to the FeNiCoCrMn/Pd high-entropy alloys,we successfully improve the prediction accuracy in a small data set and predict the concentrationdependent formation energies,lattices,and magnetic moments in quinary systems.This study provides a new algorithm to improve the performance and usability of deep learning with structures as inputs,which is effective and accurate for the prediction and development of materials for small data sets.
