基于机器学习模型的北海市银海区小流域地表水中铵氮污染预测  

Prediction of ammonium nitrogen pollution in surface water in small watersheds of Yinhai,Beihai City based on machine learning models

作　　者：涂兵 杨博 王令占 李响 谢国刚 马筱 张宗言 TU Bing;YANG Bo;WANG Lingzhan;LI Xiang;XIE Guogang;MA Xiao;ZHANG Zongyan(Wuhan Centre of Geological Survey(Central South China Innovation Center for Geosciences),China Geological Survey,Wuhan 430205,China)

机构地区：[1]中国地质调查局武汉地质调查中心(中南地质科技创新中心),湖北武汉430205

出　　处：《安全与环境工程》2024年第1期224-230,共7页Safety and Environmental Engineering

基　　金：中国地质调查局地质调查项目(DD20211385、DD20211139、DD20230104)。

摘　　要：北海市银海区小流域(冯家江流域、三合口江流域和福成河流域)地表水富营养化问题严峻,然而对地表水中铵氮(NH_(4)^(+)-N)浓度的预测研究较少。采用多元线性回归、支持向量机和随机森林3种机器学习模型,利用北海市银海区小流域地表水水质全分析数据,预测了研究区地表水中NH_(4)^(+)-N浓度的空间分布。结果表明:随机森林模型的均方根误差中值最低,拟合效果最佳,预测得到的地表水中NH_(4)^(+)-N浓度空间分布与实际NH_(4)^(+)-N浓度分布高度一致;NH_(4)^(+)-N浓度超过地表水劣Ⅴ类限值2mg/L的地表水主要分布在冯家江流域;PO_(4)^(3-)、HCO_(3)^(-)和总碱度是研究区地表水中NH_(4)^(+)-N污染最显著的指示因子,这与人类活动密不可分。The issue of eutrophication in surface water of small watersheds(Fengjiajiang River,Sanhekou River,and Fucheng River)in Yinhai,Beihai City,is of grave concern.However,there has been limited research on the prediction of surface water ammonium nitrogen(NH_(4)^(+)-N)levels.In this study,three machine learning models,namely multiple linear regression,support vector machine and random forest,were employed to predict the spatial distribution of NH_(4)^(+)-N in small watersheds of Yinhai,Beihai City,using comprehensive water quality analysis data.The results indicate that in multiple experiments,the random forest model consistently exhibited the lowest median root mean square error and the best fitting performance,showing a high degree of consistency with observed NH_(4)^(+)-N distribution in surface water.Based on the results,areas with NH_(4)^(+)-N concentrations exceeding the ClassⅤwater quality standard limit of 2 mg/Lare mainly in Fengjiajiang River.Furthermore,PO_(4)^(2-),HCO_(3)^(-),and total alkalinity are identified as the most significant indicator factors contributing to the enrichment of NH_(4)^(+)-N in surface water,highlighting the undeniable influence of human activities on surface water pollution.

关 键 词：地表水 铵氮污染 机器学习模型 北海市 

分 类 号：X522[环境科学与工程—环境工程]