Novel applications of generative adversarial networks (GANs) in the analysis of ultrafast electron diffraction (UED) images

被引:0
|
作者
Daoud, Hazem [1 ]
Sirohi, Dhruv [2 ]
Mjeku, Endri [3 ]
Feng, John [1 ]
Oghbaey, Saeed [1 ]
Miller, R. J. Dwayne [4 ]
机构
[1] Univ Toronto, Dept Phys, Toronto, ON M5S 1A7, Canada
[2] Univ Toronto, Dept Engn Sci, Toronto, ON M5S 1A7, Canada
[3] Univ Toronto, Dept Math, Toronto, ON M5S 1A7, Canada
[4] Univ Toronto, Dept Phys & Chem, Toronto, ON M5S 3H6, Canada
来源
JOURNAL OF CHEMICAL PHYSICS | 2023年 / 159卷 / 04期
关键词
MAPPING ATOMIC MOTIONS; ULTRABRIGHT ELECTRONS; CAPTURING CHEMISTRY;
D O I
10.1063/5.0154871
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
Inferring transient molecular structural dynamics from diffraction data is an ambiguous task that often requires different approximation methods. In this paper, we present an attempt to tackle this problem using machine learning. Although most recent applications of machine learning for the analysis of diffraction images apply only a single neural network to an experimental dataset and train it on the task of prediction, our approach utilizes an additional generator network trained on both synthetic and experimental data. Our network converts experimental data into idealized diffraction patterns from which information is extracted via a convolutional neural network trained on synthetic data only. We validate this approach on ultrafast electron diffraction data of bismuth samples undergoing thermalization upon excitation via 800 nm laser pulses. The network was able to predict transient temperatures with a deviation of less than 6% from analytically estimated values. Notably, this performance was achieved on a dataset of 408 images only. We believe that employing this network in experimental settings where high volumes of visual data are collected, such as beam lines, could provide insights into the structural dynamics of different samples.
引用
收藏
页数:10
相关论文
共 50 条
  • [21] Evolutionary Multiobjective Optimization Driven by Generative Adversarial Networks (GANs)
    He, Cheng
    Huang, Shihua
    Cheng, Ran
    Tan, Kay Chen
    Jin, Yaochu
    IEEE TRANSACTIONS ON CYBERNETICS, 2021, 51 (06) : 3129 - 3142
  • [22] A systematic review of generative adversarial networks (GANs) in plastic surgery
    Zargaran, Alexander
    Sousi, Sara
    Glynou, Sevasti P.
    Mortada, Hatan
    Zargaran, David
    Mosahebi, Afshin
    JOURNAL OF PLASTIC RECONSTRUCTIVE AND AESTHETIC SURGERY, 2024, 95 : 377 - 385
  • [23] Loss Functions of Generative Adversarial Networks (GANs): Opportunities and Challenges
    Pan, Zhaoqing
    Yu, Weijie
    Wang, Bosi
    Xie, Haoran
    Sheng, Victor S.
    Lei, Jianjun
    Kwong, Sam
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2020, 4 (04): : 500 - 522
  • [24] Generative Adversarial Networks (GANs) for Retinal Fundus Image Synthesis
    Bellemo, Valentina
    Burlina, Philippe
    Yong, Liu
    Wong, Tien Yin
    Ting, Daniel Shu Wei
    COMPUTER VISION - ACCV 2018 WORKSHOPS, 2019, 11367 : 289 - 302
  • [25] Creating Synthetic Test Data by Generative Adversarial Networks (GANs) for Mobile Health (mHealth) Applications
    Ahmad, Nadeem
    Feroz, Irum
    Ahmad, Faizan
    FORTHCOMING NETWORKS AND SUSTAINABILITY IN THE AIOT ERA, VOL 1, FONES-AIOT 2024, 2024, 1035 : 322 - 332
  • [26] A novel measure to evaluate generative adversarial networks based on direct analysis of generated images
    Shuyue Guan
    Murray Loew
    Neural Computing and Applications, 2021, 33 : 13921 - 13936
  • [27] A novel measure to evaluate generative adversarial networks based on direct analysis of generated images
    Guan, Shuyue
    Loew, Murray
    NEURAL COMPUTING & APPLICATIONS, 2021, 33 (20): : 13921 - 13936
  • [28] Generating OCT B-Scan DME images using optimized Generative Adversarial Networks (GANs)
    Tripathi, Aditya
    Kumar, Preetham
    Mayya, Veena
    Tulsani, Akshat
    HELIYON, 2023, 9 (08)
  • [29] Automatic Fiducial Marker Detection in Prostate Cancer MR Images Using Generative Adversarial Networks (GANs)
    Singhrao, K.
    Fu, J.
    Kishan, A.
    Lewis, J.
    MEDICAL PHYSICS, 2019, 46 (06) : E516 - E516
  • [30] Generating synthetic hypoxia images from FDG-PET using Generative Adversarial Networks (GANs)
    Traverso, A.
    Rao, C.
    Briassouli, A.
    Dekker, A.
    De Ruysscher, D.
    van Elmpt, W.
    RADIOTHERAPY AND ONCOLOGY, 2022, 170 : S1396 - S1397