基于RF-TOPSIS-MCS的水库水质综合评价方法及应用  

RF-TOPSIS-MCS-Based Comprehensive Evaluation Method for Reservoir Water Quality and Its Application

作　　者：张冲 陈末 ZHANG Chong;CHEN Mo(College of Water Resources and Electricity,Heilongjiang University,Harbin 150080,Heilongjiang,China;Cold Zone Groundwater Research Institute,Heilongjiang University,Harbin 150080,Heilongjiang,China)

机构地区：[1]黑龙江大学水利电力学院,黑龙江哈尔滨150080 [2]黑龙江大学寒区地下水研究所,黑龙江哈尔滨150080

出　　处：《水力发电》2025年第1期5-10,共6页Water Power

基　　金：黑龙江省普通本科高等学校青年创新人才培养计划(UNPYSCT-2020012)。

摘　　要：在水库管理中,准确评估水质至关重要。然而,数据收集的不确定性和水质因子权重分配的局限性均会对评估结果产生影响。为了解决这一问题,以大伙房水库为研究对象,开发了一种新的水质综合评价方法,该方法结合了随机森林算法(RF)、优劣解距离法(TOPSIS)和蒙特卡洛模拟(MCS)。首先根据实测的月均水质数据,通过MCS生成了一组正态分布的数据集。然后,利用RF赋权为TOPSIS方法分配权重,并借助隶属函数对水质进行综合评价。通过计算分析,得出的结果与辽宁省的月度水环境质量状况报告提供的水质等级相符,这表明此方法能为大型水库的水质评估提供有力的技术支持。In the management of reservoirs,accurate assessment of water quality is crucial.However,uncertainties in data collection and limitations in the allocation of weights to water quality factors can both impact the evaluation results.To address these issues,a novel method which integrates Random Forest(RF)classification prediction,Technique for Order Preference by Similarity to Ideal Solution(TOPSIS),and Monte Carlo Simulation(MCS)is developed for comprehensive water quality evaluation using the Dahuofang Reservoir as a study case.Initially,a dataset with a normal distribution is generated using MCS based on the actual monthly average water quality data.Subsequently,the RF is utilized for weight assignment in the TOPSIS method and a membership function is employed for the comprehensive evaluation of water quality.The results of case study are consistent with the water quality grades provided in the monthly water environmental quality reports of Liaoning Province,indicating that the proposed approach can provide robust technical support for the water quality assessment of large reservoirs.

关 键 词：随机森林赋权 优劣解距离法 蒙特卡罗模拟 水库水质评价 

分 类 号：X832[环境科学与工程—环境工程]