Pore Water Pressure Prediction Based on Machine Learning Methods—Application to an Earth Dam Case

Author:

An Lu1,Dias Daniel1ORCID,Carvajal Claudio2ORCID,Peyras Laurent2ORCID,Breul Pierre3ORCID,Jenck Orianne1ORCID,Guo Xiangfeng4

Affiliation:

1. CNRS, Grenoble INP, University Grenoble Alpes, 3SR, 38000 Grenoble, France

2. INRAE, RECOVER, Aix Marseille University, 13182 Aix-en-Provence, France

3. Institut Pascal, CNRS, University Clermont Auvergne, 63000 Clermont-Ferrand, France

4. School of Marine Science and Engineering, South China University of Technology, Guangzhou 510641, China

Abstract

Pore water pressure (PWP) response is significant for evaluating the earth dams’ stability, and PWPs are, therefore, generally monitored. However, due to the soil heterogeneity and its non-linear behavior within earths, the PWP is usually difficult to estimate and predict accurately in order to detect a pathology or anomaly in the behavior of an embankment dam. This study endeavors to tackle this challenge through the application of diverse machine learning (ML) techniques in estimating the PWP within an existing earth dam. The methods employed include random forest (RF) combined with simulated annealing (SA), multilayer perceptron (MLP), standard recurrent neural networks (RNNs), and gated recurrent unit (GRU). The prediction capability of these techniques was gauged using metrics such as the coefficient of determination (R2), mean square error (MSE), and CPU training time. It was found that all the considered ML methods could give satisfactory results for the PWP estimation. Upon comparing these methods within the case study, the findings suggest that, in this study, multilayer perceptron (MLP) gives the most accurate PWP prediction, achieving the highest coefficient of determination (R2 = 0.99) and the lowest mean square error (MSE = 0.0087) metrics. A sensitivity analysis is then presented to evaluate the models’ robustness and the hyperparameter’s influence on the performance of the prediction model.

Funder

China Scholarship Council

Publisher

MDPI AG

Reference50 articles.

1. Analysis of Earth Dam Response to Earthquakes;Scott;J. Geotech. Eng.,1979

2. Behavior of an Earth Dam during Rapid Drawdown of Water in Reservoir—Case Study;Fattah;Int. J. Adv. Res.,2015

3. Machine learning for pore-water pressure time-series prediction: Application of recurrent neural networks;Wei;Geosci. Front.,2021

4. An analytical model for the monitoring of pore water pressure inside embankment dams;Guo;Eng. Struct.,2018

5. Analytical solutions for calculating pore-water pressure in an infinite unsaturated slope with different root architectures;Ng;Can. Geotech. J.,2015

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3