Unveiling the principle descriptor for predicting the electron inelastic mean free path based on a machine learning framework
[4];
[7];
- Univ. of Science and Technology of China, Hefei (China). Hefei National Lab. for Physical Sciences at Microscale. Dept. of Physics; National Inst. for Materials Science (NIMS), Tsukuba (Japan). Research and Services Division of Materials Data and Integrated System; National Inst. for Materials Science (NIMS), Tsukuba (Japan). Research Center for Advanced Measurement and Characterization; DOE/OSTI
- Chinese Academy of Sciences (CAS), Fuzhou (China). Fujian Inst. of Research on the Structure of Matter. State Key Lab. of Structural Chemistry
- Univ. of Science and Technology of China, Hefei (China). Hefei National Lab. for Physical Sciences at Microscale. Dept. of Physics; National Inst. for Materials Science (NIMS), Tsukuba (Japan). Research and Services Division of Materials Data and Integrated System; National Inst. for Materials Science (NIMS), Tsukuba (Japan). Research Center for Advanced Measurement and Characterization
- National Inst. for Materials Science (NIMS), Tsukuba (Japan). Research and Services Division of Materials Data and Integrated System; National Inst. for Materials Science (NIMS), Tsukuba (Japan). Research Center for Advanced Measurement and Characterization
- National Inst. for Materials Science (NIMS), Tsukuba (Japan). Research and Services Division of Materials Data and Integrated System
- National Inst. for Materials Science (NIMS), Tsukuba (Japan). Research Center for Advanced Measurement and Characterization
- Ames Lab., Ames, IA (United States)
- Univ. of Science and Technology of China, Hefei (China). Hefei National Lab. for Physical Sciences at Microscale. Dept. of Physics
The TPP-2M formula is the most popular empirical formula for the estimation of the electron inelastic mean free paths (IMFPs) in solids from several simple material parameters. The TPP-2M formula, however, poorly describes several materials because it relies heavily on the traditional least-squares analysis. Herein, we propose a new framework based on machine learning to overcome the weakness. This framework allows a selection from an enormous number of combined terms (descriptors) to build a new formula that describes the electron IMFPs. The resulting framework not only provides higher average accuracy and stability but also reveals the physics meanings of several newly found descriptors. Using the identified principle descriptors, a complete physics picture of electron IMFPs is obtained, including both single and collective electron behaviors of inelastic scattering. Our findings suggest that machine learning is robust and efficient to predict the IMFP and has great potential in building a regression framework for data-driven problems. Furthermore, this method could be applicable to find empirical formula for given experimental data using a series of parameters given a priori, holds potential to find a deeper connection between experimental data and a priori parameters.
- Research Organization:
- Ames Laboratory (AMES), Ames, IA (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC)
- Grant/Contract Number:
- AC02-07CH11358
- OSTI ID:
- 1625098
- Journal Information:
- Science and Technology of Advanced Materials, Journal Name: Science and Technology of Advanced Materials Journal Issue: 1 Vol. 20; ISSN 1468-6996
- Publisher:
- IOP PublishingCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
Material dependence of electron inelastic mean free paths at low energies
Design and analysis of machine learning exchange-correlation functionals via rotationally invariant convolutional descriptors