Cargando…
Unveiling the principle descriptor for predicting the electron inelastic mean free path based on a machine learning framework
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...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Taylor & Francis
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6882444/ https://www.ncbi.nlm.nih.gov/pubmed/31807220 http://dx.doi.org/10.1080/14686996.2019.1689785 |
_version_ | 1783474163349979136 |
---|---|
author | Liu, Xun Hou, Zhufeng Lu, Dabao Da, Bo Yoshikawa, Hideki Tanuma, Shigeo Sun, Yang Ding, Zejun |
author_facet | Liu, Xun Hou, Zhufeng Lu, Dabao Da, Bo Yoshikawa, Hideki Tanuma, Shigeo Sun, Yang Ding, Zejun |
author_sort | Liu, Xun |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-6882444 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | Taylor & Francis |
record_format | MEDLINE/PubMed |
spelling | pubmed-68824442019-12-05 Unveiling the principle descriptor for predicting the electron inelastic mean free path based on a machine learning framework Liu, Xun Hou, Zhufeng Lu, Dabao Da, Bo Yoshikawa, Hideki Tanuma, Shigeo Sun, Yang Ding, Zejun Sci Technol Adv Mater Engineering and Structural materials 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. Taylor & Francis 2019-11-07 /pmc/articles/PMC6882444/ /pubmed/31807220 http://dx.doi.org/10.1080/14686996.2019.1689785 Text en © 2019 The Author(s). Published by National Institute for Materials Science in partnership with Taylor & Francis Group. http://creativecommons.org/licenses/by/4.0/ This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Engineering and Structural materials Liu, Xun Hou, Zhufeng Lu, Dabao Da, Bo Yoshikawa, Hideki Tanuma, Shigeo Sun, Yang Ding, Zejun Unveiling the principle descriptor for predicting the electron inelastic mean free path based on a machine learning framework |
title | Unveiling the principle descriptor for predicting the electron inelastic mean free path based on a machine learning framework |
title_full | Unveiling the principle descriptor for predicting the electron inelastic mean free path based on a machine learning framework |
title_fullStr | Unveiling the principle descriptor for predicting the electron inelastic mean free path based on a machine learning framework |
title_full_unstemmed | Unveiling the principle descriptor for predicting the electron inelastic mean free path based on a machine learning framework |
title_short | Unveiling the principle descriptor for predicting the electron inelastic mean free path based on a machine learning framework |
title_sort | unveiling the principle descriptor for predicting the electron inelastic mean free path based on a machine learning framework |
topic | Engineering and Structural materials |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6882444/ https://www.ncbi.nlm.nih.gov/pubmed/31807220 http://dx.doi.org/10.1080/14686996.2019.1689785 |
work_keys_str_mv | AT liuxun unveilingtheprincipledescriptorforpredictingtheelectroninelasticmeanfreepathbasedonamachinelearningframework AT houzhufeng unveilingtheprincipledescriptorforpredictingtheelectroninelasticmeanfreepathbasedonamachinelearningframework AT ludabao unveilingtheprincipledescriptorforpredictingtheelectroninelasticmeanfreepathbasedonamachinelearningframework AT dabo unveilingtheprincipledescriptorforpredictingtheelectroninelasticmeanfreepathbasedonamachinelearningframework AT yoshikawahideki unveilingtheprincipledescriptorforpredictingtheelectroninelasticmeanfreepathbasedonamachinelearningframework AT tanumashigeo unveilingtheprincipledescriptorforpredictingtheelectroninelasticmeanfreepathbasedonamachinelearningframework AT sunyang unveilingtheprincipledescriptorforpredictingtheelectroninelasticmeanfreepathbasedonamachinelearningframework AT dingzejun unveilingtheprincipledescriptorforpredictingtheelectroninelasticmeanfreepathbasedonamachinelearningframework |