防灾减灾工程学报2025，Vol.45Issue(5)：1032-1041,10.DOI:10.13409/j.cnki.jdpme.20250417002
基于DL-ERT模型的地下水渗透系数预测方法研究
Research on Prediction Method for Groundwater Permeability Coefficient Based on DL-ERT Model
摘要
Abstract
To address the issues of insufficient accuracy and high prediction costs faced by convention-al methods in characterizing the heterogeneity of groundwater aquifers,this study proposed a physics-informed deep learning algorithm—the DL-ERT model—based on numerical simulations and laborato-ry sandbox experiments.The model integrated the powerful data learning capability of a convolutional gated recurrent unit(CNN-GRU)optimized by residual networks with the advantage of physical prior information from electrical resistivity tomography(ERT).The DL-ERT model was compared with multiple traditional inversion models to examine the accuracy of the fusion algorithm in characterizing the permeability coefficient of groundwater aquifers.The results showed that:(1)the training and vali-dation losses of the DL-ERT model rapidly decreased and approached zero,and their convergence was almost synchronous,indicating that the construction strategy of the DL-ERT model was excel-lent and that data features could be quickly and effectively learned.(2)Taking a sample from the test set as an example,the inversion cloud maps of the permeability coefficient obtained by ERT,CNN-GRU,and DL-ERT were compared.It was found that individual algorithm models could not simulta-neously capture the high-permeability zones on both sides,while DL-ERT demonstrated remarkable predictive potential for high-permeability zones,achieving a fitting accuracy of 0.906.(3)Laboratory sandbox experiments were conducted,and the fusion algorithm was compared with traditional Kriging interpolation,CNN-GRU,and ERT,yielding fitting accuracies of 0.895,0.707,0.760,and 0.836,respectively.It is evident that the DL-ERT model compensates for the limitations of individual algo-rithms to some extent,with prediction accuracy improved by 7%-17%compared with the individual CNN-GRU and ERT models,indicating the potential of the model for engineering applications.关键词
渗透系数/电阻率层析/卷积门控循环单元/物理规律/反演预测Key words
permeability coefficient/resistivity tomography/convolutional gated recurrent unit/physi-cal laws/inversion prediction分类
建筑与水利引用本文复制引用
梁越,舒云林,刘港庆,许彬,赵硕,杨晓霞..基于DL-ERT模型的地下水渗透系数预测方法研究[J].防灾减灾工程学报,2025,45(5):1032-1041,10.基金项目
国家自然科学基金面上项目(52379097)、广西科技计划项目(桂科AA23062023)、重庆市水利科技重点项目(CQSLK-2024005)、重庆市研究生联合培养基地建设项目(JDLHPYJD2021004)、重庆交通大学研究生科研创新项目(2024S0049)资助 （52379097）
