A back propagation neural network-based approach for inverting layered seabed acoustic parameters in shallow waters

• DOI: 10.3389/fmars.2024.1349478
• Publication Date: 2024-02-28T05:09:35Z
• Authors: Jiahui Wang; Zhiqiang Cui; Hanhao Zhu; Lei Meng; Weihua Song; Xu Liu
• Keywords: Seabed

Introduction Existing methods primarily focus on earth acoustic parameters inversion under specific layered structures. However, they face challenges with experimental data from unknown seabed stratification, hindering accurate parameter inversion. Methods To address this, a novel algorithm combines Back Propagation Neural Network (BPNN) for distinguishing stratification and inverting parameters. Simulated sound pressure disturb as input, enabling feature recognition training the neural network model. Acoustic are then estimated identified using field Results The model is validated simulation pool shrinkage data. show effectively stratifies data, providing results corresponding to distinct layers. Discussion model's accuracy practicality confirmed through hierarchical judgment of scale test This approach introduces new perspective shallow sea inversion, offering promising application scenario.