Skip to main content

ORIGINAL RESEARCH article

Front. Mar. Sci.
Sec. Ocean Observation
Volume 12 - 2025 | doi: 10.3389/fmars.2025.1484098

An Estimation method of sound speed profile based on Grouped Dilated Convolution Informer Model

Provisionally accepted
Siyuan Qin Siyuan Qin 1*Yi Zhang Yi Zhang 2Zhou Chen Zhou Chen 3
  • 1 Zhengzhou Professional Technical Institute of Electronic & Information, Zheng Zhou, China
  • 2 School of Marine Sciences, Sun Yat-sen University, Zhuhai Campus, Zhuhai, Guangdong Province, China
  • 3 College of Marine Science and Engineering, Nanjing Normal University, Nanjing, Liaoning Province, China

The final, formatted version of the article will be published soon.

    The accurate determination of the ocean sound speed profile (SSP) is essential for oceanographic research and marine engineering. Traditional methods for acquiring SSP data are often time-consuming and costly. Machine learning techniques provide a more efficient alternative for SSP inversion, effectively addressing the limitations of conventional approaches. This study proposes a novel SSP inversion model based on a grouped dilated convolution (GDC) Informer architecture. By replacing the standard one-dimensional convolution in the Informer model with GDC, the proposed model expands its receptive field and improves computational efficiency. The model was trained using Argo profile data from 2008 to 2017, incorporating empirical orthogonal function (EOF) decomposition data, geographic location, temporal information, and historical SSP data, enabling SSP inversion across diverse regions and time periods. The model's performance was evaluated using mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) metrics. Experimental results demonstrate that the Informer-GDC model achieves evaluation metrics of 0.355 m/s and 0.611 m/s for MAE, 0.241 m/s and 0.394 m/s for RMSE, and 0.018% and 0.025% for MAPE compared with measured data from 2018. Compared to the LSTM and Informer models, the proposed model improves MAE, RMSE, and MAPE by 46.51% and 29.66%, 51.65% and 39.28%, and 51.25% and 37.08%, respectively. These findings highlight the superior accuracy, stability, and efficiency of the Informer-GDC model, marking a significant advancement in SSP inversion methodologies.

    Keywords: Sound speed profile, inversion, Grouped dilated convolution, Informer model, Empirical orthogonal decomposition

    Received: 21 Aug 2024; Accepted: 16 Jan 2025.

    Copyright: © 2025 Qin, Zhang and Chen. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Siyuan Qin, Zhengzhou Professional Technical Institute of Electronic & Information, Zheng Zhou, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.