水利学报Issue(5)：521-528,8.DOI:10.13243/j.cnki.slxb.2014.05.003
含水层渗透系数预测及不确定性分析耦合模型
A coupling model for aquifer hydraulic conductivity prediction and its uncertainty analysis
摘要
Abstract
This study aims at fine calculation of alluvial-proluvial plain region and providing fundamental data for construction of solute transport model in the further research. Hydraulic conductivities of aquifers in the study area are predicted through establishing a coupling model between artificial neural network (ANN) and generalized likelihood uncertainty estimation (GLUE), and uncertainty of the model parameters is analyzed. Markov Chain Monte Carlo (MCMC) was used to replace Monte Carlo (MC) in common GLUE, and coupled it with artificial neural network technology, an overall model of aquifer hydraulic con-ductivity prediction and its uncertainty analysis (GLUE-ANN) was built by using 150 typical grain-size fraction samples as input data. Via case study in a typical area of North China Plain the study corroborates a better sampling efficiency and optimization capability; compared to measured values of hydraulic conductivi-ty, relative errors of the GLUE-ANN model are between 1.55 % and 23.53 %, the calculation precision of the model meets the requirements of groundwater resources assessment. By posterior distributions of the mod-el parameters, the areas of parameter global optimum are obtained, which indicates the model is capable of reasonably reflecting parameter uncertainty of hydrogeological model.关键词
渗透系数/ANN技术/贝叶斯方法/GLUE/MCMC/不确定性Key words
hydraulic conductivity/ANN/Bayesian/GLUE/MCMC/uncertainty分类
天文与地球科学引用本文复制引用
桂春雷,石建省,刘继朝,马荣..含水层渗透系数预测及不确定性分析耦合模型[J].水利学报,2014,(5):521-528,8.基金项目
国家重点基础研究发展计划（973）计划项目（20100CB428800）；中国地质科学院水文地质环境地质研究所项目 （）
