Robust activation energy predictions of solute diffusion from machine learning method

• Published in: Computational materials science 2020-11, Vol.184, p.109948, Article 109948
• Main Authors: He, Kang-ni, Kong, Xiang-shan, Liu, C.S.
• Format: Article
• Language: English
• Subjects: Activation energy; Diffusion; Machine learning; Support vector machine
• ISSN: 0927-0256; 1879-0801
• DOI: 10.1016/j.commatsci.2020.109948

[Display omitted] •Develop prediction method for solute diffusion in fcc, bcc and hcp metallic hosts.•Obtain an optimal set of features of solute and host for machine learning method.•Predict new data of solute diffusion activation energies in metallic hosts.•The machine learning method can accelerate materials science researches. We evaluate the performance of a popular machine learning (ML) method support vector machine (SVM) for modeling and predicting the solute diffusion activation energies in fcc, bcc, and hcp metallic hosts. The diffusion activation energies of 408 host-solute systems from ab-initio calculations are made as our dataset. We obtain an optimal set of features by combining prior physics knowledge and combination ranking based on the Leave-Group-Out (LOG) cross-validation (CV) method, including solute migration barrier, atomic volume of host, elastic modulus of host, melting point of host, unpaired d electrons of host, and the corresponding parameters of solute. We present the results of LOG/10-fold/5-fold/3-fold CV, with the corresponding root mean squared error (RMSE) of 0.128/0.106 ± 0.014/0.107 ± 0.004/0.110 ± 0.005 eV. SVM gives an about 0.1 eV errors when extrapolating to new host-solute systems for main hosts. We further make predictions on the activation energies of thousands of new systems with quite small computational cost. Our work demonstrates that the ML method is a promising method to accelerate materials science researches.