Your new experience awaits. Try the new design now and help us make it even better

ORIGINAL RESEARCH article

Front. Mar. Sci.

Sec. Ocean Solutions

Volume 12 - 2025 | doi: 10.3389/fmars.2025.1615580

This article is part of the Research TopicBig Data and AI for Sustainable Maritime OperationsView all 9 articles

Comparative study of machine learning and deep learning in predicting the shear strength of marine sand and polymer layer interfaces interface under marine temperature effects

Provisionally accepted
Zhiming  ChaoZhiming Chao1Yanqi  LiuYanqi Liu1Dongbo  JiangDongbo Jiang2Hongbo  DuHongbo Du3Wei  YouWei You3Xianhui  FengXianhui Feng4Jie  linJie lin5Peng  CuiPeng Cui6,7*Zejin  WangZejin Wang8*
  • 1Shanghai Maritime University, pudong, Shanghai, China
  • 2PowerChina Kunming Engineering Co. Ltd, Kunming, Yunnan Province, China
  • 3Chongqing Jiaotong University, Nan'an District, Chongqing Municipality, China
  • 4University of Science and Technology Beijing, Beijing, Beijing Municipality, China
  • 5CCCC Fourth Harbor Engineering Institute Co., Ltd, Guangzhou, China
  • 6Nanjing Forestry University, Nanjing, China
  • 7Umeå University, Umeå, Västerbotten, Sweden
  • 8Nanjing Tech University, Nanjing, Jiangsu Province, China

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

In marine engineering, polymer layers are anti-seepage barrier materials. The mechanical interaction between marine sand and polymer layer significantly affects overall structural stability. In this study, direct shear tests at different temperatures in the marine environment are simulated to evaluate the shear behavior of marine sand and polymer layer interface, and a database is developed. Based on the experimental data, the study employs the Back propagation Neural Network (BPNN), Genetic Algorithm and Particle Swarm Optimization BPNN, and convolutional neural network (CNN) models, which are trained and tested. The findings show that the CNN algorithm significantly outperforms other models in terms of prediction accuracy and efficiency. Sensitivity analysis shows that temperature, shear displacement, normal stress, and particle size have influence on interfacial shear strength, and the impact of normal stress is the greatest. In addition, an empirical formulation is proposed to provide tools for those without machine learning. Based on the research results, the deep learning CNN model developed in the study can accurately predict the shear strength of the interface between marine sand and the polymer layer , which provides an effective tool for the design and optimization of marine engineering.

Keywords: Marine sand and polymer layer interface, temperature, Convolutional Neural Network, Shear Strength, machine learning

Received: 21 Apr 2025; Accepted: 24 Sep 2025.

Copyright: © 2025 Chao, Liu, Jiang, Du, You, Feng, lin, Cui and Wang. 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:
Peng Cui, cui.peng@umu.se
Zejin Wang, 18625087602@163.com

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.