Evaluation of exit gradient of hydraulic structures with cut-off walls in explainable machine learning surrogate based on numerical models

Author:

Rath Prayas1ORCID,Zhu Jianting1,Befus Kevin M.2

Affiliation:

1. University of Wyoming

2. University of Arkansas Fayetteville: University of Arkansas

Abstract

Abstract

We develop machine learning surrogate models based on XGBoost to predict the exit gradients that are critical in optimizing hydraulic structure design and overcoming limitations of analytical methods regarding anisotropy and boundary effects. For the XGBoost model, we use 8000 MODFLOW numerical simulations covering diverse parameters affecting groundwater flow under hydraulic structures, including anisotropy, head differentials, structure width, cut-off wall depth, aquifer thickness, and uninterrupted riverbed length. We train 60% of the MODFLOW models with a coefficient of determination above 0.99. Upon cross validating, the coefficient of determination across ten splits of training data was 0.71 indicating minimal overfitting. The coefficient of determination for test data is 0.88 demonstrating reliable exit gradient prediction by the XGBoost. For explainability of the XGBoost model, we implement the SHAP (SHapley Additive exPlanations) framework. Feature selection using the SHAP values identify the anisotropy and the ratio of cut-off wall depth to aquifer thickness as the primary influencers on the exit gradients. Notably, anisotropy's impact is more pronounced when the cut-off wall is relatively smaller compared to the hydraulic structure's width. Additionally, the influence of cut-off wall depth diminishes with higher vertical anisotropy. This analysis enhances understanding of exit gradient control factors and establishing subsurface anisotropy as a crucial factor in hydraulic structure designs regarding the exit gradient.

Publisher

Research Square Platform LLC

Reference33 articles.

1. a. Linked simulation-optimization model for optimum hydraulic design of water retaining structures constructed on permeable soils;Al-Juboori M;Int J GEOMATE,2018

2. Al-Juboori M, Datta B (2018) b. Predicting Exit Gradient of Water Retaining Structures: a Comparative Study of Five Machine Learning Techniques. Proceedings of Academicsera 18th International Conference, Melbourne, Australia, (July), 8–16

3. Minimum Cost Design of Hydraulic Water Retaining Structure by using Coupled Simulation Optimization Approach;Al-Juboori M;KSCE J Civ Eng,2019

4. Scripting MODFLOW Model Development Using Python and FloPy;Bakker M;Groundwater,2016

5. ANN-GA-Based Model for Multiple Objective Management of Coastal Aquifers;Bhattacharjya RK;J Water Resour Plan Manag,2009

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

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