基于数据驱动的地下水-地表水耦合模拟  

Data-Driven Coupled Groundwater-Surface Water Modelling

作　　者：孙俊峰 胡浩鑫 曾献奎[2] SUN Junfeng;HU Haoxin;ZENG Xiankui(Safety and Environmental Protection Supervision Department,National Energy Group Ningxia Coal Co.,Ltd.,Yinchuan 750411,China;School of Earth Sciences and Engineering,Nanjing University,Nanjing 210023,China)

机构地区：[1]国家能源集团宁夏煤业有限责任公司安全环保监察部,宁夏银川750411 [2]南京大学地球科学与工程学院,江苏南京210023

出　　处：《水文》2025年第2期15-22,共8页Journal of China Hydrology

基　　金：国家重点研发计划项目“场地未定标特征污染物甄别、风险评估与分级分类方法”(2022YFC3703203)。

摘　　要：地下水-地表水耦合模型是定量刻画地下水地表水相互作用及流域水文循环的重要工具。随着人工智能的兴起,基于数据驱动的机器学习方法在地表水或地下水模拟领域取得重要进展,克服了传统水文数值模型面临的困难。然而,目前缺乏基于数据驱动方法的地下水-地表水耦合模型。提出基于深度学习的地下水-地表水耦合模拟技术,利用多任务卷积神经网络(CNN)和长短期记忆神经网络(LSTM)方法,以美国加利福尼亚州的Sagehen流域为研究区,构建基于数据驱动的地下水-地表水耦合模型预测河流日径流量和地下水位。结果表明,基于CNN和LSTM建立的深度学习模型对研究区地表径流量模拟的纳什效率系数(NSE)为0.8094,对地下水位模拟的NSE高于0.81,模拟效果较好。研究成果可为流域地下水-地表水耦合模拟提供新思路。The coupled groundwater-surface water model is an essential tool for quantitatively characterizing the interactions between groundwater and surface water as well as hydrological processes in watersheds.With the rise of artificial intelligence,datadriven machine learning methods have made significant advancements in the field of surface water or groundwater simulation,overcoming challenges faced by traditional hydrological numerical models.However,a data-driven groundwater-surface water coupling model that simultaneously predicts both surface runoff and groundwater levels has not been observed thus far.By combining multitask Convolutional Neural Networks(CNN)and Long Short-Term Memory(LSTM)neural networks,this study constructed a datadriven coupled model for the Sagehen watershed,simultaneously predicting river runoff and groundwater levels.The results indicate that the deep learning model established on CNN and LSTM achieves a Nash-Sutcliffe Efficiency coefficient(NSE)of 0.8094 for simulating surface runoff and an NSE higher than 0.81 for simulating groundwater levels in the study area,demonstrating satisfactory simulation performance.The findings could offer new insights into watershed groundwater-surface water coupling simulation.

关 键 词：数据驱动 深度学习 地下水与地表水 耦合模型 

分 类 号：P641.6[天文地球—地质矿产勘探] P343[天文地球—地质学]