Applying machine learning to balance performance and stability of high energy density materials

Xiaona Huang; Chongyang Li; Kaiyuan Tan; Yushi Wen; Feng Guo; Ming Li; Yongli Huang; Chang Q Sun; Michael Gozin; Lei Zhang

doi:10.1016/j.isci.2021.102240

Applying machine learning to balance performance and stability of high energy density materials

iScience. 2021 Feb 26;24(3):102240. doi: 10.1016/j.isci.2021.102240. eCollection 2021 Mar 19.

Authors

Xiaona Huang^{1

2

3}, Chongyang Li^{2

4}, Kaiyuan Tan¹, Yushi Wen¹, Feng Guo⁵, Ming Li¹, Yongli Huang², Chang Q Sun^{6

7}, Michael Gozin^{8

9

10}, Lei Zhang^{2

11}

Affiliations

¹ Institute of Chemical Materials, China Academy of EngineeringPhysics (CAEP), Mianyang, 621900, China.
² CAEP Software Center for High Performance Numerical Simulation, Beijing, 100088, China.
³ Department of Mechanical Engineering, City University of Hong Kong, 83 Tat Chee Avenue, Kowloon, 999077, Hong Kong, China.
⁴ Key Laboratory of Low-dimensional Materials and Application Technology (Ministry of Education), School of Materials Science and Engineering, Xiangtan University, Xiangtan, 411105, China.
⁵ School of Physical Science and Information Technology, Liaocheng University, Liaocheng, 252000, China.
⁶ EBEAM, Yangtze Normal University, Chongqing, 408100, China.
⁷ NOVITAS, Nanyang Technological University, Singapore, 639798, Singapore.
⁸ School of Chemistry, Faculty of Exact Science, Tel Aviv University, Tel Aviv, 69978, Israel.
⁹ Tel Aviv University Center for Nanoscience and Nanotechnology, Tel Aviv, 69978, Israel.
¹⁰ Center of Advanced Combustion Science, Tel Aviv University, Tel Aviv, 69978, Israel.
¹¹ Laboratory of Computational Physics, Institute of Applied Physics and Computational Mathematics, Beijing, 100088, China.

Abstract

The long-standing performance-stability contradiction issue of high energy density materials (HEDMs) is of extremely complex and multi-parameter nature. Herein, machine learning was employed to handle 28 feature descriptors and 5 properties of detonation and stability of 153 HEDMs, wherein all 21,648 data used were obtained through high-throughput crystal-level quantum mechanics calculations on supercomputers. Among five models, namely, extreme gradient boosting regression tree (XGBoost), adaptive boosting, random forest, multi-layer perceptron, and kernel ridge regression, were respectively trained and evaluated by stratified sampling and 5-fold cross-validation method. Among them, XGBoost model produced the best scoring metrics in predicting the detonation velocity, detonation pressure, heat of explosion, decomposition temperature, and lattice energy of HEDMs, and XGBoost predictions agreed best with the 1,383 experimental data collected from massive literatures. Feature importance analysis was conducted to obtain data-driven insight into the causality of the performance-stability contradiction and delivered the optimal range of key features for more efficient rational design of advanced HEDMs.

Keywords: Computational Materials Science; Computational Method in Materials Science; Energy Materials; Materials Design.