一种基于污染风险的地下水监测井网多目标优化方法  

Multi-objective Optimization Method for Groundwater Pollution Monitoring Well Network Based on Pollution Risk

作　　者：闫聪 林斯杰 邓泽政 杨庆 刘明柱[1] YAN Cong;LIN Sijie;DENG Zezheng;YANG Qing;LIU Mingzhu(School of Water Resources and Environment,China University of Geosciences(Beijing),Beijing 100083,China;School of Environmental Science and Engineering,Southern University of Science and Technology,Shenzhen 518055,China;Beijing Institute of Geology and Mineral Resources Exploration,Beijing 100048,China)

机构地区：[1]中国地质大学(北京)水资源与环境学院,北京100083 [2]南方科技大学环境科学与工程学院,广东深圳518055 [3]北京市地质矿产勘察院,北京100048

出　　处：《安全与环境工程》2021年第3期240-248,共9页Safety and Environmental Engineering

基　　金：京津冀地下水污染防治关键技术研究与工程示范项目(2018ZX07109-002);北京市自然科学基金项目(8181002)。

摘　　要：地下水具有重要的生态服务功能。地下水监测可为管理和维护地下水生态安全提供必要的信息。如何以最低的监测成本获取最丰富的地下水信息一直是科学家和管理者关注的热点问题之一。在模拟退火算法的基础上,利用随机森林算法筛选出对地下水质量演化指示性最强的监测指标,并结合水文地质分析法,考虑地下水污染风险性,以监测成本最低、精度最高和不确定性最小为目标函数,建立了区域地下水污染监测井网多目标优化模型,最后通过北京市平谷盆地平原区的示范应用,验证了该方法的有效性。结果表明:多目标优化模型的Pareto最优解显示,示范区地下水污染监测井的最优数量为29口,冗余监测井为3口,为提高监测精度需新增监测井5口;示范区地下水污染监测井网优化前后NO-3-N浓度的相对误差小于20%,低于接受阈值,证明该方法具有可靠性,可为平原地区地下水污染监测井网布设提供一种指示性强且快速的多目标优化方法。Groundwater has important ecological service functions.The monitoring provides necessary information for the management and maintenance safety for groundwater ecology.How to obtain the richest groundwater information at the lowest monitoring cost has always been one of the interests for scientists and managers.Taking the lowest monitoring cost,the highest monitoring accuracy and the lowest uncertainty as the objective function,this study establishes a multi-objective optimization model of groundwater pollution monitoring wells based on pollution risk assessment,constructs an importance screening model for groundwater monitoring indicators by random forest methods,uses simulated annealing algorithm to solve the multi-objective optimization model,and finally demonstratse an application in plain area of Pinggu Basin in Beijing.The result show that the Pareto optimal solution of the model indicates that optimal and redundant regional groundwater monitoring wells are 29 and 3,and five wells should be increased to improve the monitoring accuracy.The relative error of NO-3-N concentration at the monitoring wells before and after the optimization is below 20%,less than the threshold,indicating that the method is valid,highly indicative and of fast multi-objective optimization for groundwater pollution monitoring well network design.

关 键 词：地下水污染 监测井网设计 多目标优化 模拟退火算法 随机森林算法 

分 类 号：X84[环境科学与工程—环境工程] X832