geoacoustic inversion;
deep learning;
transformer model;
2-D positional embedding;
D O I:
10.3390/jmse11061108
中图分类号:
U6 [水路运输];
P75 [海洋工程];
学科分类号:
0814 ;
081505 ;
0824 ;
082401 ;
摘要:
Geoacoustic inversion is a challenging task in marine research due to the complex environment and acoustic propagation mechanisms. With the rapid development of deep learning, various designs of neural networks have been proposed to solve this issue with satisfactory results. As a data-driven method, deep learning networks aim to approximate the inverse function of acoustic propagation by extracting knowledge from multiple replicas, outperforming conventional inversion methods. However, existing deep learning networks, mainly incorporating stacked convolution and fully connected neural networks, are simple and may neglect some meaningful information. To extend the network backbone for geoacoustic inversion, this paper proposes a transformer-based geoacoustic inversion model with additional frequency and sensor 2-D positional embedding to perceive more information from the acoustic input. The simulation experimental results indicate that our proposed model achieves comparable inversion results with the existing inversion networks, demonstrating its effectiveness in marine research.
机构:
Academy of Medical Engineering and Translational Medicine,Tianjin University
Tianjin Key Laboratory of Brain Science and Neural Engineering,Tianjin UniversityAcademy of Medical Engineering and Translational Medicine,Tianjin University
机构:
China Univ Geosci Beijing, Sch Informat Engn, Beijing 100083, Peoples R China
Chinese Acad Sci, Inst Elect Engn, Beijing Int S&T Cooperat Base Plasma Sci & Energy, Beijing 100190, Peoples R ChinaChina Univ Geosci Beijing, Sch Informat Engn, Beijing 100083, Peoples R China
Guo, Jiyuan
Zhao, Shicheng
论文数: 0引用数: 0
h-index: 0
机构:
Chinese Acad Sci, Inst Elect Engn, Beijing Int S&T Cooperat Base Plasma Sci & Energy, Beijing 100190, Peoples R China
Univ Chinese Acad Sci, Beijing 100049, Peoples R ChinaChina Univ Geosci Beijing, Sch Informat Engn, Beijing 100083, Peoples R China
Zhao, Shicheng
Huang, Bangdou
论文数: 0引用数: 0
h-index: 0
机构:
Chinese Acad Sci, Inst Elect Engn, Beijing Int S&T Cooperat Basefor Plasma Sci & Ener, Beijing 100190, Peoples R ChinaChina Univ Geosci Beijing, Sch Informat Engn, Beijing 100083, Peoples R China
Huang, Bangdou
Wang, Hang
论文数: 0引用数: 0
h-index: 0
机构:
Hubei Univ Technol, Hubei Engn Res Ctr Safety Mon itoring New Energy &, Wuhan 430068, Peoples R ChinaChina Univ Geosci Beijing, Sch Informat Engn, Beijing 100083, Peoples R China
Wang, Hang
He, Yi
论文数: 0引用数: 0
h-index: 0
机构:
China Univ Geosci Beijing, Sch Informat Engn, Beijing 100083, Peoples R ChinaChina Univ Geosci Beijing, Sch Informat Engn, Beijing 100083, Peoples R China
He, Yi
Zhang, Chuyan
论文数: 0引用数: 0
h-index: 0
机构:
China Univ Geosci Beijing, Sch Informat Engn, Beijing 100083, Peoples R ChinaChina Univ Geosci Beijing, Sch Informat Engn, Beijing 100083, Peoples R China
Zhang, Chuyan
Zhang, Cheng
论文数: 0引用数: 0
h-index: 0
机构:
Chinese Acad Sci, Inst Elect Engn, Beijing Int S&T Cooperat Base Plasma Sci & Energy, Beijing 100190, Peoples R China
Univ Chinese Acad Sci, Beijing 100049, Peoples R ChinaChina Univ Geosci Beijing, Sch Informat Engn, Beijing 100083, Peoples R China
Zhang, Cheng
Shao, Tao
论文数: 0引用数: 0
h-index: 0
机构:
Chinese Acad Sci, Inst Elect Engn, Beijing Int S&T Cooperat Base Plasma Sci & Energy, Beijing 100190, Peoples R China
Univ Chinese Acad Sci, Beijing 100049, Peoples R ChinaChina Univ Geosci Beijing, Sch Informat Engn, Beijing 100083, Peoples R China