摘要
准确掌握地下水的环境质量状况是合理确定地下水资源开发策略和有效进行地下水资源保护的重要前提。通过随机森林(randomforest)法构建弥河-潍河流域地下水质量评价模型,结果表明:(1)随机森林法在进行地下水水质分类时具有分类精度高、泛化能力强等特点,且在进行超参数优化后,其分类精度会进一步提高,证明将随机森林法应用于地下水质量评价是可行的,并且其综合性能要优于逻辑回归模型;(2)研究区地下水水样均为Ⅳ类和Ⅴ类水,说明水质状况整体较差;(3)通过分类指标重要性评价可以看出,研究区地下水水质的主要影响指标为硝酸盐、总硬度和溶解性总固体,而此类指标的主要来源是蔬菜种植化肥的不合理使用及河流污染入渗,因此要进一步加强对蔬菜种植污染排放及河流水质的监测和控制。
Accurately assessment of groundwater quality is an prerequisite for effective exploitation and protection of groundwater resources.A groundwater quality assessment model for the Mihe-Weihe River basin was constructed based on random forest algo-rithm.The results show that,(1)random forest algorithm has high accuracy and strong generalization ability for groundwater quality classfication;moreover,after hyperparameter optimization,its classification accuracy will be further improved,which shows that the random forest based model is excellently suited for groundwater quality assessment,and its comprehensive performance is better than the logistic regression model;(2)the groundwater samples are all classified as Class Ⅳand Ⅴ,indicating poor groundwater quality;(3)the importance of classification indicators show that the main influeneing indicators of groundwater quality in this study area are nitrate,total hardness and total dissolved solids,and the main sources of such indicators are from unreasonable use of fertilizers and infilration of river pollution.Therefore,it is necessary to further strengthen the monitoring and control of pollution emissions from vegetable planting and river water quality.
作者
林艳竹
韩忠
黄林显
邢立亭
梁浩
侯金霄
LIN Yanzhu;HAN Zhong;HUANG Linxian;XING Liting;LIANG Hao;HOU Jinxiao(China Geological Environment Monitoring Instiute(Geological Disaster Technical Guidance Center),Bejjing 100081,China;Institution of Geology and Mineral Resources Exploration of Shandong Province,Weihai 264209,China;School of Water Conservancy and Environment,University of Jinan,Jinan 250022,China;Engineering Technology Instiute for Groundwater Numerical Simulation and Contamination Control,Jinan 250022,China;Shandong Provincial Space Ecological Restoration Center,Jinan 250014,China)
出处
《水文》
CSCD
北大核心
2023年第3期60-64,70,共6页
Journal of China Hydrology
基金
国家自然科学基金资助项目(41772257)
山东省自然科学基金资助项目(ZR2019MD029)
山东省高校院所创新团队项目(2021GXRC070)
院科研基金项目(801KY202004)。
关键词
机器学习
随机森林法
弥河-潍河流域
地下水质量评价
machine learning
random forest algorithm
Mihe-Weihe River basin
groundwater quality assessment