Phase-field-based models have become common in material science, mechanics, physics, biology, chemistry, and engineering for the simulation of microstructure evolution. Yet, they suffer from the drawback of being computationally very costly when applied to large, complex systems. To reduce such computational costs, a Unet-based artificial neural network is developed as a surrogate model in the current work. Training input for this network is obtained from the results of the numerical solution of initial-boundary-value problems (IBVPs) based on the Fan-Chen model for grain microstructure evolution. In particular, about 250 different simulations with varying initial order parameters are carried out and 200 frames of the time evolution of the phase fields are stored for each simulation. The network is trained with 90% of this data, taking the $i$-th frame of a simulation, i.e. order parameter field, as input, and producing the $(i+1)$-th frame as the output. Evaluation of the network is carried out with a test dataset consisting of 2200 microstructures based on different configurations than originally used for training. The trained network is applied recursively on initial order parameters to calculate the time evolution of the phase fields. The results are compared to the ones obtained from the conventional numerical solution in terms of the errors in order parameters and the system's free energy. The resulting order parameter error averaged over all points and all simulation cases is 0.005 and the relative error in the total free energy in all simulation boxes does not exceed 1%.
Accelerating Phonon Thermal Conductivity Prediction by an Order of Magnitude Through Machine Learning-Assisted Extraction of Anharmonic Force Constants
Accelerating Finite-temperature Kohn-Sham Density Functional Theory with Deep Neural Networks
Sandia National Laboratories(桑迪亚国家实验室);Center for Advanced Systems Understanding (CASUS)(高级系统理解中心(CASUS));Helmholtz-Zentrum Dresden-Rossendorf(亥姆霍兹德累斯顿罗森多夫研究中心)
Accelerating the discovery of low-energy structure configurations: a computational approach that integrates first-principles calculations, Monte Carlo sampling, and Machine Learning
Accelerating the Training and Improving the Reliability of Machine-Learned Interatomic Potentials for Strongly Anharmonic Materials through Active Learning
Accelerating dynamic simulations of photoexcited materials and their evolution by electron-informed machine learning
Beijing National Laboratory for Condensed Matter Physics and Institute of Physics, Chinese Academy of Sciences(中国科学院物理研究所凝聚态物理国家实验室);School of Physical Sciences, University of Chinese Academy of Sciences(中国科学院大学物理科学学院);Songshan Lake Materials Laboratory(松山湖材料实验室)
Accelerating Electronic Stopping Power Predictions by 10 Million Times with a Combination of Time-Dependent Density Functional Theory and Machine Learning
Data Science and Learning Division, Argonne National Laboratory(阿贡国家实验室数据科学与学习部);Department of Computer Science, The University of Chicago(芝加哥大学计算机科学系);Department of Materials Science and Engineering, University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校材料科学与工程系)
Accelerating the Design of Resorbable Magnesium Alloys: A Machine Learning Approach to Property Prediction
FZU - Institute of Physics, Czech Academy of Sciences(捷克科学院物理研究所);Department of Materials, Faculty of Nuclear Sciences and Physical Engineering, Czech Technical University in Prague(布拉格捷克技术大学核科学与物理工程学院材料系)
Accelerating the Discovery of g-C$_3$N$_4$-Supported Single Atom Catalysts for Hydrogen Evolution Reaction: A Combined DFT and Machine Learning Strategy
由单原子催化(SAC)支撑的二维材料有望取代铂,用于可持续制氢的大规模工业可扩展性。在这里,一系列的金属(Al、Sc、Ti、V、Cr、Mn、Fe、Ni、Cu、Zn)和非金属通过DFT计算和六种机器学习(ML)算法筛选出嵌入g-C $_3$ N $_4$不同活性位点的(B,C,N,O,F,Si,P,S,Cl)单原子(支持向量回归,梯度提升回归,随机森林回归,AdaBoost回归,多层感知器回归,岭回归)。基于形成能、吉布斯自由能和能带分析的结果表明,B、Mn和Co的单原子锚定在g-C $_3$ N $_4$上可以作为高效的产氢活性中心。基于支持向量回归(SVR)的ML模型表现出最好的性能,准确和快速地预测吉布斯氢吸附自由能($Δ$ GH)的测试集与较低的平均绝对误差(MAE)和高决定系数(R $^2$)的0.45和0.81,分别。基于SVR模型的特征选择突出了前五个主要特征:形成能、键长、沸点、熔点和价电子作为关键描述符。总之,通过DFT计算结合ML模型用于有效筛选g-C $_3$ N $_4$基单原子催化的潜在析氢反应(HER)的多步工作流程可以显著地有助于催化剂设计和制造。
Accelerating Discovery of Vacancy Ordered 18-Valence Electron Half-Heusler Compounds: A Synergistic Approach of Machine Learning and Density Functional Theory