Reconstructing the Semiconductor Band Structure by Deep Learning

Shidong Yang; Xiwang Liu; Jinyan Lin; Ruixin Zuo; Xiaohong Song; Marcelo Ciappina; Weifeng Yang

doi:10.3390/math10224268

Reconstructing the Semiconductor Band Structure by Deep Learning

Shidong Yang, Xiwang Liu, Jinyan Lin, Ruixin Zuo, Xiaohong Song, Marcelo Ciappina^*, Weifeng Yang

^*Corresponding author for this work

Physics

Research output: Contribution to journal › Article › peer-review

Abstract

High-order harmonic generation (HHG), the nonlinear upconversion of coherent radiation resulting from the interaction of a strong and short laser pulse with atoms, molecules and solids, represents one of the most prominent examples of laser–matter interaction. In solid HHG, the characteristics of the generated coherent radiation are dominated by the band structure of the material, which configures one of the key properties of semiconductors and dielectrics. Here, we combine an all-optical method and deep learning to reconstruct the band structure of semiconductors. Our method builds up an artificial neural network based on the sensitivity of the HHG spectrum to the carrier-envelope phase (CEP) of a few-cycle pulse. We analyze the accuracy of the band structure reconstruction depending on the predicted parameters and propose a prelearning method to solve the problem of the low accuracy of some parameters. Once the network is trained with the mapping between the CEP-dependent HHG and the band structure, we can directly predict it from experimental HHG spectra. Our scheme provides an innovative way to study the structural properties of new materials.

Original language	English
Journal	Mathematics
Volume	10
Issue number	22
DOIs	https://doi.org/10.3390/math10224268
State	Published - 15 Nov 2022

Access to Document

10.3390/math10224268

https://www.mdpi.com/2227-7390/10/22/4268/pdf?version=1669004391License: CC BY

Cite this

@article{b7d7baea089a4f96a1a8bd7febc0e4db,

title = "Reconstructing the Semiconductor Band Structure by Deep Learning",

abstract = "High-order harmonic generation (HHG), the nonlinear upconversion of coherent radiation resulting from the interaction of a strong and short laser pulse with atoms, molecules and solids, represents one of the most prominent examples of laser–matter interaction. In solid HHG, the characteristics of the generated coherent radiation are dominated by the band structure of the material, which configures one of the key properties of semiconductors and dielectrics. Here, we combine an all-optical method and deep learning to reconstruct the band structure of semiconductors. Our method builds up an artificial neural network based on the sensitivity of the HHG spectrum to the carrier-envelope phase (CEP) of a few-cycle pulse. We analyze the accuracy of the band structure reconstruction depending on the predicted parameters and propose a prelearning method to solve the problem of the low accuracy of some parameters. Once the network is trained with the mapping between the CEP-dependent HHG and the band structure, we can directly predict it from experimental HHG spectra. Our scheme provides an innovative way to study the structural properties of new materials.",

author = "Shidong Yang and Xiwang Liu and Jinyan Lin and Ruixin Zuo and Xiaohong Song and Marcelo Ciappina and Weifeng Yang",

year = "2022",

month = nov,

day = "15",

doi = "10.3390/math10224268",

language = "英语",

volume = "10",

journal = "Mathematics",

issn = "2227-7390",

publisher = "MDPI AG",

number = "22",

}

TY - JOUR

T1 - Reconstructing the Semiconductor Band Structure by Deep Learning

AU - Yang, Shidong

AU - Liu, Xiwang

AU - Lin, Jinyan

AU - Zuo, Ruixin

AU - Song, Xiaohong

AU - Ciappina, Marcelo

AU - Yang, Weifeng

PY - 2022/11/15

Y1 - 2022/11/15

N2 - High-order harmonic generation (HHG), the nonlinear upconversion of coherent radiation resulting from the interaction of a strong and short laser pulse with atoms, molecules and solids, represents one of the most prominent examples of laser–matter interaction. In solid HHG, the characteristics of the generated coherent radiation are dominated by the band structure of the material, which configures one of the key properties of semiconductors and dielectrics. Here, we combine an all-optical method and deep learning to reconstruct the band structure of semiconductors. Our method builds up an artificial neural network based on the sensitivity of the HHG spectrum to the carrier-envelope phase (CEP) of a few-cycle pulse. We analyze the accuracy of the band structure reconstruction depending on the predicted parameters and propose a prelearning method to solve the problem of the low accuracy of some parameters. Once the network is trained with the mapping between the CEP-dependent HHG and the band structure, we can directly predict it from experimental HHG spectra. Our scheme provides an innovative way to study the structural properties of new materials.

AB - High-order harmonic generation (HHG), the nonlinear upconversion of coherent radiation resulting from the interaction of a strong and short laser pulse with atoms, molecules and solids, represents one of the most prominent examples of laser–matter interaction. In solid HHG, the characteristics of the generated coherent radiation are dominated by the band structure of the material, which configures one of the key properties of semiconductors and dielectrics. Here, we combine an all-optical method and deep learning to reconstruct the band structure of semiconductors. Our method builds up an artificial neural network based on the sensitivity of the HHG spectrum to the carrier-envelope phase (CEP) of a few-cycle pulse. We analyze the accuracy of the band structure reconstruction depending on the predicted parameters and propose a prelearning method to solve the problem of the low accuracy of some parameters. Once the network is trained with the mapping between the CEP-dependent HHG and the band structure, we can directly predict it from experimental HHG spectra. Our scheme provides an innovative way to study the structural properties of new materials.

U2 - 10.3390/math10224268

DO - 10.3390/math10224268

M3 - 文章

SN - 2227-7390

VL - 10

JO - Mathematics

JF - Mathematics

IS - 22

ER -

Reconstructing the Semiconductor Band Structure by Deep Learning

Abstract

Access to Document

Fingerprint

Cite this