Deep Learning Infrared Holography with Transformer for Crystal Material Characterization

Zijian Li; Haochong Huang; Dexin Sun; Zhiyuan Zheng; Fang Wang; Spozmai Panezai; Jie Xing; Yehua Yang; Kunfeng Qiu

doi:10.1021/acs.cgd.4c00919

Deep Learning Infrared Holography with Transformer for Crystal Material Characterization

Zijian Li, Haochong Huang, Dexin Sun, Zhiyuan Zheng, Fang Wang, Spozmai Panezai, Jie Xing, Yehua Yang, Kunfeng Qiu

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

9 Scopus citations

Abstract

This investigation presents a novel approach for the nondestructive, and real-time analysis of crystalline structures, including transition metal dichalcogenides renowned for their optoelectronic capabilities. The methodology employs a synergistic blend of infrared digital holography and deep learning, utilizing an in-line system and Transformer-based deep learning algorithms, to provide detail in the material microstructure. The article investigates the effects of different parameters on reproduction fidelity, with a particular focus on phase accuracy. A holography-guided training strategy is proposed to enhance the framework’s performance. By demonstration applications such as evaluating the dielectric characteristics of ReS₂, detecting material thickness layers in MoS₂, and monitoring the microstructure evolution during the growth of NaCl and CuSO₄ crystals. Not only addresses existing limitations in material characterization but also offers avenues for exploration.

Original language	English
Pages (from-to)	6851-6864
Number of pages	14
Journal	Crystal Growth and Design
Volume	24
Issue number	16
DOIs	https://doi.org/10.1021/acs.cgd.4c00919
State	Published - Aug 21 2024
Externally published	Yes

Funding

This work is supported by the National Natural Science Foundation of China (61805214, 42072087), Open Fund of State Key Laboratory of Infrared Physics (SITP-NLIST-YB-2024-12), Piesat Information Technology remote sensing interdisciplinary research project (HTHT202202),the Fundamental Research Funds for the Central Universities (2-9-2022-203). Young Elite Scientists Sponsorship Program by Bast (BYESS2020037), Frontiers Science Center for Deep-time Digital Earth (2652023001).

Access to Document

10.1021/acs.cgd.4c00919

Cite this

@article{2c245b77599242efb3352b92ca45bbef,

title = "Deep Learning Infrared Holography with Transformer for Crystal Material Characterization",

abstract = "This investigation presents a novel approach for the nondestructive, and real-time analysis of crystalline structures, including transition metal dichalcogenides renowned for their optoelectronic capabilities. The methodology employs a synergistic blend of infrared digital holography and deep learning, utilizing an in-line system and Transformer-based deep learning algorithms, to provide detail in the material microstructure. The article investigates the effects of different parameters on reproduction fidelity, with a particular focus on phase accuracy. A holography-guided training strategy is proposed to enhance the framework{\textquoteright}s performance. By demonstration applications such as evaluating the dielectric characteristics of ReS2, detecting material thickness layers in MoS2, and monitoring the microstructure evolution during the growth of NaCl and CuSO4 crystals. Not only addresses existing limitations in material characterization but also offers avenues for exploration.",

author = "Zijian Li and Haochong Huang and Dexin Sun and Zhiyuan Zheng and Fang Wang and Spozmai Panezai and Jie Xing and Yehua Yang and Kunfeng Qiu",

note = "Publisher Copyright: {\textcopyright} 2024 American Chemical Society.",

year = "2024",

month = aug,

day = "21",

doi = "10.1021/acs.cgd.4c00919",

language = "English",

volume = "24",

pages = "6851--6864",

journal = "Crystal Growth and Design",

issn = "1528-7483",

publisher = "American Chemical Society",

number = "16",

}

TY - JOUR

T1 - Deep Learning Infrared Holography with Transformer for Crystal Material Characterization

AU - Li, Zijian

AU - Huang, Haochong

AU - Sun, Dexin

AU - Zheng, Zhiyuan

AU - Wang, Fang

AU - Panezai, Spozmai

AU - Xing, Jie

AU - Yang, Yehua

AU - Qiu, Kunfeng

PY - 2024/8/21

Y1 - 2024/8/21

N2 - This investigation presents a novel approach for the nondestructive, and real-time analysis of crystalline structures, including transition metal dichalcogenides renowned for their optoelectronic capabilities. The methodology employs a synergistic blend of infrared digital holography and deep learning, utilizing an in-line system and Transformer-based deep learning algorithms, to provide detail in the material microstructure. The article investigates the effects of different parameters on reproduction fidelity, with a particular focus on phase accuracy. A holography-guided training strategy is proposed to enhance the framework’s performance. By demonstration applications such as evaluating the dielectric characteristics of ReS2, detecting material thickness layers in MoS2, and monitoring the microstructure evolution during the growth of NaCl and CuSO4 crystals. Not only addresses existing limitations in material characterization but also offers avenues for exploration.

AB - This investigation presents a novel approach for the nondestructive, and real-time analysis of crystalline structures, including transition metal dichalcogenides renowned for their optoelectronic capabilities. The methodology employs a synergistic blend of infrared digital holography and deep learning, utilizing an in-line system and Transformer-based deep learning algorithms, to provide detail in the material microstructure. The article investigates the effects of different parameters on reproduction fidelity, with a particular focus on phase accuracy. A holography-guided training strategy is proposed to enhance the framework’s performance. By demonstration applications such as evaluating the dielectric characteristics of ReS2, detecting material thickness layers in MoS2, and monitoring the microstructure evolution during the growth of NaCl and CuSO4 crystals. Not only addresses existing limitations in material characterization but also offers avenues for exploration.

UR - http://www.scopus.com/inward/record.url?scp=85200815110&partnerID=8YFLogxK

U2 - 10.1021/acs.cgd.4c00919

DO - 10.1021/acs.cgd.4c00919

M3 - Article

AN - SCOPUS:85200815110

SN - 1528-7483

VL - 24

SP - 6851

EP - 6864

JO - Crystal Growth and Design

JF - Crystal Growth and Design

IS - 16

ER -

Deep Learning Infrared Holography with Transformer for Crystal Material Characterization

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Cite this