Predicting Elastic Properties of Materials from Electronic Charge Density Using 3D Deep Convolutional Neural Networks
University of South Carolina（南卡罗来纳大学）；Dalian University of Technology（大连理工大学）；Key Laboratory of Ocean Energy Utilization and Energy Conservation of Ministry of Education（教育部海洋能源利用与节能重点实验室）；Key Laboratory of Materials Modification by Laser, Ion and Electron Beams（教育部激光、离子、电子束材料改性重点实验室）；School of Energy and Power Engineering（能源与动力工程学院）
Yong Zhao, Kunpeng Yuan, Yinqiao Liu, Steph-Yves Louis, Ming Hu, Jianjun Hu
Materials representation plays a key role in machine learning based prediction of materials properties and new materials discovery. Currently both graph and 3D voxel representation methods are based on the heterogeneous elements of the crystal structures. Here, we propose to use electronic charge density (ECD) as a generic unified 3D descriptor for materials property prediction with the advantage of possessing close relation with the physical and chemical properties of materials. We developed an ECD based 3D convolutional neural networks (CNNs) for predicting elastic properties of materials, in which CNNs can learn effective hierarchical features with multiple convolving and pooling operations. Extensive benchmark experiments over 2,170 Fm-3m face-centered-cubic (FCC) materials show that our ECD based CNNs can achieve good performance for elasticity prediction. Especially, our CNN models based on the fusion of elemental Magpie features and ECD descriptors achieved the best 5-fold cross-validation performance. More importantly, we showed that our ECD based CNN models can achieve significantly better extrapolation performance when evaluated over non-redundant datasets where there are few neighbor training samples around test samples. As additional validation, we evaluated the predictive performance of our models on 329 materials of space group Fm-3m by comparing to DFT calculated values, which shows better prediction power of our model for bulk modulus than shear modulus. Due to the unified representation power of ECD, it is expected that our ECD based CNN approach can also be applied to predict other physical and chemical properties of crystalline materials.
Transferable 3D Convolutional Neural Networks for Elastic Constants Prediction in Nanoporous Metals
Universidad Carlos III de Madrid（马德里卡洛斯三世大学）；IMDEA Materials Institute（IMDEA材料研究所）；Institute of Mathematics, Polish Academy of Sciences（波兰科学院数学研究所）；Faculty of Mechanical Engineering, Technion-Israel Institute of Technology（以色列理工学院机械工程学院）
Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networks
Claremont Graduate University（克莱蒙特研究生大学）；Pomona College（波莫纳学院）；San Diego State University（圣地亚哥州立大学）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；Broadridge Financial Solutions（百瑞吉金融解决方案公司）；Institute of Mathematical Sciences（数学科学研究所）；Mathematics Department（数学系）；Computational Science Research Center（计算科学研究中心）；Earth and Environmental Sciences Division（地球与环境科学部）
Predicting Mechanical Properties of Lignin-Containing Polyurethane Rigid Foams from Microstructure Using Convolutional Neural Networks
Notre Dame University-Louaize（黎巴嫩美国大学）；American University of Beirut（贝鲁特美国大学）；Scion Group, Bioeconomy Science Institute（斯坎集团生物经济科学研究所）；Flemish Institute for Technological Research (VITO)（弗拉芒技术研究所）；University of Antwerp（安特卫普大学）
