Comparative evaluation of machine learning models for assessment of seabed liquefaction using finite element data

Aug 3, 2026

Upload by Ezra

Wave-induced liquefaction around submarine pipelines is essential to assess for offshore engineering safety, yet traditional numerical methods struggle with the complex coupling between ocean dynamics and seabed sediments and the need for rapid, accurate predictions. This study compares four classical machine learning models—Gradient Boosting, Support Vector Machine, Multi-Layer Perceptron, and Random Forest—using finite element data. Results show Gradient Boosting delivers higher stability and accuracy, with performance varying by output parameter and input combination. Machine learning also substantially reduces computation time, supporting rapid disaster assessment and early warning.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Introduction

Seabed liquefaction and pipeline safety

Related work on scouring, pore pressure, and analytical/numerical modeling

TYPE Original Research PUBLISHED 15 November 2024 DOI 10.3389/fmars.2024.1491899 OPEN ACCESS EDITED BY Charlotte Lyddon, University of Liverpool, United Kingdom REVIEWED BY Andre´s Payo, The Lyell Centre, United Kingdom Songdong Shao, Dongguan University of Technology, China *CORRESPONDENCE Yupeng Song songyupeng@ﬁ[o.org.cn](o.org.cn) Dong Wang [dongwang@ouc.edu.cn](dongwang@ouc.edu.cn) RECEIVED 05 September 2024 ACCEPTED 23 October 2024 PUBLISHED 15 November 2024 CITATION Du X, Song Y, Wang D, He K, Chi W, Xiu Z and Zhao X (2024) Comparative evaluation of machine learning models for assessment of seabed liquefaction using ﬁnite element data. Front. Mar. Sci. 11:1491899 . doi: 10.3389/fmars.2024.1491899 COPYRIGHT © 2024 Du, Song, Wang, He, Chi, Xiu and Zhao. 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) and the copyright owner(s) 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. Comparative evaluation of machine learning models for assessment of seabed liquefaction using ﬁnite element data Xing Du 1,2, Yupeng Song 1*, Dong Wang 2*, Kunpeng He 3, Wanqing Chi 1, Zongxiang Xiu 1 and Xiaolong Zhao 1 1 Engineering Center, First Institute of Oceanography, Ministry of Natural Resources (MNR), Qingdao, China, 2College of Environmental Science and Engineering, Ocean University of China, Qingdao, China, 3State Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan, China Predicting wave-induced liquefaction around submarine pipelines is crucial for marine engineering safety. However, the complex of interactions between ocean dynamics and seabed sediments makes rapid and accurate assessments challenging with traditional numerical methods. Although machine learning approaches are increasingly applied to wave-induced liquefaction problems, the comparative accuracy of different models remains under-explored. We evaluate the predictive accuracy of four classical machine learning models: Gradient Boosting (GB), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Random Forest (RF) . The results indicate that the GB model exhibits high stability and accuracy in predicting wave-induced liquefaction, due to its strong ability to handle complex nonlinear geological data. Prediction accuracy varies across output parameters, with higher accuracy for seabed predictions than for pipeline surroundings. The combination of different input parameters signiﬁcantly inﬂuences model predictive accuracy. Compared to traditional ﬁnite element numerical methods, employing machine learning models signiﬁcantly reduces computation time, offering an effective tool for rapid disaster assessment and early warning in marine engineering. This research contributes to the safety of marine pipeline protections and provides new insights into the intersection of marine geological engineering and artiﬁcial intelligence. KEYWORDS submarine pipelines, gradient boosting, support vector machine, machine learning, wave-current coupling Frontiers in Marine Science 01 [frontiersin.org](frontiersin.org) 1 Introduction Submarine pipelines are vital infrastructures in the global energy supply chain, connecting terrestrial and marine resources to transport critical energy resources such as crude oil and natural gas. With the continuous expansion of offshore resource exploration, ensuring the stability of submarine pipelines under extreme geological conditions becomes crucial. One signiﬁcant challenge is the liquefaction of seabed sediments under wave action, which can jeopardize the stability and safety of these pi

FAQs

Why is seabed liquefaction assessment critical for submarine pipeline safety?

Seabed liquefaction under wave action can undermine pipeline stability and safety, so accurate predictions are necessary for offshore engineering and energy development.

Which machine learning model shows the highest predictive stability in the study?

The Gradient Boosting (GB) model demonstrates high stability and accuracy when predicting wave-induced liquefaction.

How does model performance depend on inputs and output parameters?

Prediction accuracy varies across output parameters, and combining different input parameters significantly affects model predictive accuracy.

Aug 3, 2026

Upload by Ezra