{"title":"A Neural Network Method for Inversion of Turbulence Strength","authors":"Weishi Yin, Baoyin Zhang, Pinchao Meng, Linhua Zhou, Dequan Qi","doi":"10.1007/s44198-024-00186-0","DOIUrl":null,"url":null,"abstract":"<p>Accurate inversion of atmospheric turbulence strength is a challenging problem in modern turbulence research due to its practical significance. Inspired by transfer learning, we propose a new neural network method consisting of convolution and pooling modules for the atmospheric turbulence strength inversion problem. Its input is the intensity image of the beam and its output is the refractive index structure constant characterizing the atmospheric turbulence strength. We evaluate the inversion performance of the neural network at different beams. Meanwhile, to enhance the generalisation of the network, we mix data sets from different turbulence environments to construct new data sets. Additionally, the inverted atmospheric turbulence strength is used as a priori information to help identify turbulent targets. Experimental results demonstrate the effectiveness of our proposed method.</p>","PeriodicalId":48904,"journal":{"name":"Journal of Nonlinear Mathematical Physics","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Nonlinear Mathematical Physics","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1007/s44198-024-00186-0","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATHEMATICS, APPLIED","Score":null,"Total":0}
引用次数: 0
Abstract
Accurate inversion of atmospheric turbulence strength is a challenging problem in modern turbulence research due to its practical significance. Inspired by transfer learning, we propose a new neural network method consisting of convolution and pooling modules for the atmospheric turbulence strength inversion problem. Its input is the intensity image of the beam and its output is the refractive index structure constant characterizing the atmospheric turbulence strength. We evaluate the inversion performance of the neural network at different beams. Meanwhile, to enhance the generalisation of the network, we mix data sets from different turbulence environments to construct new data sets. Additionally, the inverted atmospheric turbulence strength is used as a priori information to help identify turbulent targets. Experimental results demonstrate the effectiveness of our proposed method.
期刊介绍:
Journal of Nonlinear Mathematical Physics (JNMP) publishes research papers on fundamental mathematical and computational methods in mathematical physics in the form of Letters, Articles, and Review Articles.
Journal of Nonlinear Mathematical Physics is a mathematical journal devoted to the publication of research papers concerned with the description, solution, and applications of nonlinear problems in physics and mathematics.
The main subjects are:
-Nonlinear Equations of Mathematical Physics-
Quantum Algebras and Integrability-
Discrete Integrable Systems and Discrete Geometry-
Applications of Lie Group Theory and Lie Algebras-
Non-Commutative Geometry-
Super Geometry and Super Integrable System-
Integrability and Nonintegrability, Painleve Analysis-
Inverse Scattering Method-
Geometry of Soliton Equations and Applications of Twistor Theory-
Classical and Quantum Many Body Problems-
Deformation and Geometric Quantization-
Instanton, Monopoles and Gauge Theory-
Differential Geometry and Mathematical Physics