基于决策树的河南省主要水库水质影响因素分析
|
摘要
为了探寻影响水库水环境的主要因素,以河南省38座水库作为典型,根据其2012年的水质监测数据,采用CART决策树方法,以其中的28座为训练集,通过Modeler特征选择选出7个主要影响因素作为变量,水库水质为目标变量,建立模型,并用全部38座水库对模型进行了验证,结果表明:模型训练的准确率为100.0%,验证的准确率为94.74%;破碎度对模型的影响程度为0.43,单位面积农药施用量、单位面积施肥量、单位面积工业产值、人口密度、单位面积工业废水排放量等5个因素对模型的影响程度均为0.11,单位面积GDP对模型的影响最小,仅有0.02.决策树方法可以应用于水库的水质影响因素研究.
Taking thirty-eight reservoirs of Henan Province for typical examples, and the classification and regression tree(CART) decision tree method is adopted, and then based on the water quality monitoring data of 2012, the main factors affecting reservoir water environment are explored. Seven main factors are chosen as variables by the module of feature selection from Modeler software to build up model with twenty-eight reservoirs as training set and water quality as the goal; the model is verified by whole reservoir numbers. The research results show that the training accuracy of the model is 100%, and the rate of verifying was 94.74%; the influence of fragmentation degree is the largest with 0.43; the influence degree of applying pesticide per unit area, fertilizer rate per unit area, industrial output per unit area, population density, industrial wastewater emissions per unit area on the model are all 0.11; the effects of GDP per unit area on the model is minimum, only 0.02. It is concluded that the decision tree method can be applied to study the influencing factors on water quality for reservoirs.
Taking thirty-eight reservoirs of Henan Province for typical examples, and the classification and regression tree(CART) decision tree method is adopted, and then based on the water quality monitoring data of 2012, the main factors affecting reservoir water environment are explored. Seven main factors are chosen as variables by the module of feature selection from Modeler software to build up model with twenty-eight reservoirs as training set and water quality as the goal; the model is verified by whole reservoir numbers. The research results show that the training accuracy of the model is 100%, and the rate of verifying was 94.74%; the influence of fragmentation degree is the largest with 0.43; the influence degree of applying pesticide per unit area, fertilizer rate per unit area, industrial output per unit area, population density, industrial wastewater emissions per unit area on the model are all 0.11; the effects of GDP per unit area on the model is minimum, only 0.02. It is concluded that the decision tree method can be applied to study the influencing factors on water quality for reservoirs.
引文
[1] 陈水蓉,吴光红,苏睿先.天津市于桥水库水质变化特点及影响因素分析[J].水资源保护,2011,27(4):27-29,34.Chen Shuirong,Wu Guanghong,Su Ruixian.Change characteristics of water quality and its impact factor at the Yuqiao Reservoir in Tianjin [J].Water Resources Protection,2011,27(4):27-29,34.
[2] 武周虎.倾斜岸坡深度平均浓度分布及污染混合区解析计算[J].水利学报,2015,46(10):1172-1180.Wu Zhouhu.Analytical calculation of the depth-averaged concentration distribution and pollutant mixing zone for sloped bank[J].Journal of Hydraulic Engineering,2015,46(10):1172-1180.
[3] 马太玲 ,朝伦巴根,高瑞忠.基于人工神经网络的串联水库水质模拟预测[J].内蒙古农业大学学报(自然科学版),2010,31(2):260-264.Ma Tailing,Chaolunbagen,Gao Ruizhong.Simulation and prediction of water quality for cascade reservoirs based on A-BP [J].Journal of Inner Mongolia Agricultural University (Natural Science Edition),2010,31(2):260-264.
[4] 罗华军,刘德富,黄应平.基于遗传算法-支持向量机的水库叶绿素a浓度短期预测非线性时序模型[J].水利学报,2009,40(1):46-51.Luo Huajun,Liu Defu,Huang Yingping.Genetic algorithm support vector machine model for short-term prediction of chlorophyll a concentration nonlinear time series [J].Journal of Hydraulic Engineering,2009,40(1):46-51.
[5] 马太玲,朝伦巴根,高瑞忠,等.水质模糊贴近度模型中权值的遗传算法解[J].环境工程,2006,24(5):77-79.Ma Tailing,Chaolunbagen,Gao Ruizhong,et al.Identification of weighting parameters for water quality fuzzy nearness model by genetic algorithm [J].Environmental Engineering,2006,24(5):77-79.
[6] 易仲强,刘德富.基于WEKA平台的湖库富营养化程度智能评价研究[J].水电能源科学,2010,28(4):40-42,80.Yi Zhongqiang,Liu Defu.Research on intelligent evaluation of lake and reservoir eutrophication based on WEKA [J].Water Resources and Power,2010,28(4):40-42,80.
[7] 张银燕,李弼程.基于MIN-MAX云重心推理的目标威胁评估方法[J].系统仿真学报,2014,26(2):411-418.Zhang Yinyan,Li Bicheng.Method of target threat assessment based on cloudy MIN-MAX center of gravity reasoning [J].Journal of System Simulation,2014,26(2):411-418.
[8] 欧阳广,李倩倩,满君丰.基于DDAG-SVM的网络流量分类技术[J].数学的实践与认识,2013,43(8):197-203.Ouyang Guang,Li Qianqian,Man Junfeng.The network traffic classification techniques based on DDAG-SVM [J].Mathematics in Practice and Theory,2013,43(8):197-203.
[9] 张弛,周惠成,王本德.决策树技术在水库兴利调度中的应用研究[J].哈尔滨工业大学学报,2007,39(8):1314-1318.Zhang Chi,Zhou Huicheng,Wang Bende.Applications and researches of decision tree technology in reservoir operation [J].Journal of Harbin Institute of Technology,2007,39(8):1314-1318.
[10] 钟平安,张梦然,蔡杰,等.基于决策树的梯级水电站泄流补偿调度风险分析[J].电力系统自动化,2012,36(20):63-67,121.Zhong Pingan,Zhang Mengran,Cai Jie,et al.Risk analysis on flow discharge compensating operation for cascade hydroelectric stations based on decision tree [J].Automation of Electric Power Systems,2012,36(20):63-67,121.
[11] 习树峰,彭勇,梁国华,等.基于决策树方法的水库跨流域引水调度规则研究[J].大连理工大学学报,2012,52(1):74-78.Xi Shufeng,Pen Yong,Liang Guohua,et al.Research on reservoir operation rules of inter-basin water transfer based on decision tree method [J].Journal of Dalian University of Technology,2012,52(1):74-78.
[12] 李正云,刘艳伟,王海星.基于决策树方法的杨凌示范区水体提取分析[J].水资源与水工程学报,2013,24(6):133-135.Li Zhengyun,Liu Yanwei,Wang Haixing.Analysis of water body extraction in Yanglin demonstration zone based on decision tree method [J].Journal of Water Resources & Water Engineering,2013,24(6):133-135.
[13] 朱海涛,张霞,王树东.基于面向对象决策树算法的半干旱地区遥感影像分类[J].遥感信息,2013,28(4):50-56.Zhu Haitao,Zhang Xia,Wang Shudong.Object-oriented and decision tree classification for remote sensing data in semi-arid areas [J].Remote Sensing Information,2013,28(4):50-56.
[14] 黄珊,林玮玮,王长连,等.基于决策树的万古霉素血药浓度解读及实践[J].中国药学杂志,2016,51(19):1710-1713.Huang Shan,Lin Weiwei,Wang Changlian,et al.Interpretation of vancomycin serum concentration based on decision tree and clinical practice [J].Chinese Pharmaceutical Journal,2016,51(19):1710-1713.
[15] 刘玥,张允岭,金香兰,等.基于决策树法缺血性脑卒中与短暂性脑缺血发作患者血瘀证识别模式比较研究[J].中华中医药杂志,2015,30(5):1723-1727.Liu Yue,Zhang Yunling,Jin Xianglan,et al.Comparison study of recognization patterns of ischemic stroke and TIA patients with blood stasis syndrome based on decision tree [J].China Journal of Traditional Chinese Medicine and Pharmacy,2015,30(5):1723-1727.
[16] 卢金锁,黄廷林,韩宏大,等.基于决策树技术及在线监测的水质预测[J].环境监测管理与技术,2006,18(2):38-41.Lu Jinsuo,Huang Tinglin,Han Hongda,et al.Forecast water quality based on decision-making tree and online monitoring [J].The Administration and Technique of Environmental Monitoring,2006,18(2):38-41.
[17] 曾勇,杨志锋,刘静玲.城市湖泊水华预警模型研究-以北京“六海”为例[J].水科学进展,2007,18(1):79-85.Zeng Yong,Yang Zhifeng,Liu Jingling.Algalbloom prediction models for Liuhai Lake in Beijing city [J].Advances in Water Science,2007,18(1):79-85.
[18] 唐国磊,周惠成,李宁宁,等.一种基于决策树技术的中长期径流分级方法[J].水力发电学报,2011,30(3):45-49.Tang Guolei,Zhou Huicheng,Li Ningning,et al.Medium-and-long-term runoff classification method using decision tree technique[J].Journal of Hydroelectric Engineering,2011,30(3):45-49.
[19] 张玮,杨善林,刘婷婷.基于CART和自适应Boosting算法的移动通信企业客户流失预测模型[J].中国管理科学,2014,22(10):90-96.Zhang Wei,Yang Shanlin,Liu Tingting.Customer churn prediction in mobile communication enterprises based on CART and boosting algorithm [J].Chinese Journal of Management Science,2014,22(10):90-96.
[20] 陈平,徐星.基于CART算法的带钢抗拉强度影响因素研究[J].控制工程,2015,22(2):276-281.Chen Ping,Xu Xing.Research of tensile strength of strip steel based on CART [J].Control Engineering of China,2015,22(2):276-281.
[21] 李春鑫,李天伟.基于决策树改进CART算法的决策支持与分析技术[J].计算机科学,2004,31(9A):44-46.Li Chunxin,Li Tianwei.Decision support and analysis technique based on improved CART arithmetic of decision tree [J].Computer Science,2004,31(9A):44-46.
[22] 张博,王书航,姜霞,等.丹江口库区土地利用格局与水质响应关系[J].环境科学研究,2016,29(9):1303-1310.Zhang Bo,Wang Shuhang,Jiang Xia,et al.Response relationship research between land use patterns and water quality in Danjiangkou Reservoir[J].Research of Environmental Science,2016,29(9):1303-1310.
[23] Merem E C,Yerramilli S,Twumasi Y A,et al.The applications of GIS in the analysis of the impacts of human activities on South Texas Watersheds [J].International Journal of Environmental Research and Public Health,2011,8(6):2418-2446.
[24] Su S,Zhi J,Lou L,et al.Spatio-temporal patterns and source apportionment of pollution in Qiantang River (China) using neural-based modeling and multivariate statistical techniques [J].Physics and Chemistry of the Earth,parts A/B/C,2011,36(9-11):379-386.
[25] Wang J,Da L,Song K,et al.Temporal variations of surface water quality in urban,suburban and rural areas during rapid urbanization in Shanghai,China [J].Environmental Pollution,2008,152(2):387-393.
[26] Chang H.Spatial analysis of water quality trends in the Han River basin,South Korea [J].Water Research,2008,13:3285-3304.
[27] 王国重,蔡崇法.磨沟小流域水土流失状况及对策[J].人民长江,2008,39(18):43-44.Wang Guozhong,Cai Chongfa.Soil and water loss condition of Mogou small basin and the countermeasures [J].Yangtze River,2008,39(18):43-44.
[28] 徐静,韩兆光.岳城水库饮用水源地水体富营养化预防措施探讨[J].海河水利,2011,(4):14-17,20.Xu Jing,Han Zhaoguang.The discussion on prevention measures of eutrophication in Yuecheng Reservoir drinking water source area [J].Haihe Water Resources,2011,(4):14-17,20.
[29] 王明浩,王文杰,冯宇,等.湖南水府庙水库流域景观格局与水质特征关系分析[J].环境工程技术学报,2015,5(4):333-340.Wang Minghao,Wang Wenjie,Feng Yu,et al.Relationship of landscape pattern and river water quality in Shuifumiao Reservoir watershed in Hunan Province [J].Journal of Environmental Engineering Technology,2015,5(4):333-340.
[30] 吉冬青,文雅,魏建兵,等.流溪河流域景观空间特征与河流水质的关联分析[J].生态学报,2015,35(2):246-253.Ji Dongqing,Wen Ya,Wei Jianbing,et al.Relationships between landscape spatial characteristics and surface water quality in the Liuxi River watershed [J].Acta Ecologica Sinica,2015,35(2):246-253.
[31] 张健,陈凤,濮励杰,等.经济快速增长区土地利用变化对土壤质量影响研究[J].环境科学研究,2007,20(5):99-104.Zhang Jian,Chen Feng,Pu Lijie,et al.The land use changes and its effects on the soil properties in the rapid developed region [J].Research of Environmental Sciences,2007,20(5):99-104.
[2] 武周虎.倾斜岸坡深度平均浓度分布及污染混合区解析计算[J].水利学报,2015,46(10):1172-1180.Wu Zhouhu.Analytical calculation of the depth-averaged concentration distribution and pollutant mixing zone for sloped bank[J].Journal of Hydraulic Engineering,2015,46(10):1172-1180.
[3] 马太玲 ,朝伦巴根,高瑞忠.基于人工神经网络的串联水库水质模拟预测[J].内蒙古农业大学学报(自然科学版),2010,31(2):260-264.Ma Tailing,Chaolunbagen,Gao Ruizhong.Simulation and prediction of water quality for cascade reservoirs based on A-BP [J].Journal of Inner Mongolia Agricultural University (Natural Science Edition),2010,31(2):260-264.
[4] 罗华军,刘德富,黄应平.基于遗传算法-支持向量机的水库叶绿素a浓度短期预测非线性时序模型[J].水利学报,2009,40(1):46-51.Luo Huajun,Liu Defu,Huang Yingping.Genetic algorithm support vector machine model for short-term prediction of chlorophyll a concentration nonlinear time series [J].Journal of Hydraulic Engineering,2009,40(1):46-51.
[5] 马太玲,朝伦巴根,高瑞忠,等.水质模糊贴近度模型中权值的遗传算法解[J].环境工程,2006,24(5):77-79.Ma Tailing,Chaolunbagen,Gao Ruizhong,et al.Identification of weighting parameters for water quality fuzzy nearness model by genetic algorithm [J].Environmental Engineering,2006,24(5):77-79.
[6] 易仲强,刘德富.基于WEKA平台的湖库富营养化程度智能评价研究[J].水电能源科学,2010,28(4):40-42,80.Yi Zhongqiang,Liu Defu.Research on intelligent evaluation of lake and reservoir eutrophication based on WEKA [J].Water Resources and Power,2010,28(4):40-42,80.
[7] 张银燕,李弼程.基于MIN-MAX云重心推理的目标威胁评估方法[J].系统仿真学报,2014,26(2):411-418.Zhang Yinyan,Li Bicheng.Method of target threat assessment based on cloudy MIN-MAX center of gravity reasoning [J].Journal of System Simulation,2014,26(2):411-418.
[8] 欧阳广,李倩倩,满君丰.基于DDAG-SVM的网络流量分类技术[J].数学的实践与认识,2013,43(8):197-203.Ouyang Guang,Li Qianqian,Man Junfeng.The network traffic classification techniques based on DDAG-SVM [J].Mathematics in Practice and Theory,2013,43(8):197-203.
[9] 张弛,周惠成,王本德.决策树技术在水库兴利调度中的应用研究[J].哈尔滨工业大学学报,2007,39(8):1314-1318.Zhang Chi,Zhou Huicheng,Wang Bende.Applications and researches of decision tree technology in reservoir operation [J].Journal of Harbin Institute of Technology,2007,39(8):1314-1318.
[10] 钟平安,张梦然,蔡杰,等.基于决策树的梯级水电站泄流补偿调度风险分析[J].电力系统自动化,2012,36(20):63-67,121.Zhong Pingan,Zhang Mengran,Cai Jie,et al.Risk analysis on flow discharge compensating operation for cascade hydroelectric stations based on decision tree [J].Automation of Electric Power Systems,2012,36(20):63-67,121.
[11] 习树峰,彭勇,梁国华,等.基于决策树方法的水库跨流域引水调度规则研究[J].大连理工大学学报,2012,52(1):74-78.Xi Shufeng,Pen Yong,Liang Guohua,et al.Research on reservoir operation rules of inter-basin water transfer based on decision tree method [J].Journal of Dalian University of Technology,2012,52(1):74-78.
[12] 李正云,刘艳伟,王海星.基于决策树方法的杨凌示范区水体提取分析[J].水资源与水工程学报,2013,24(6):133-135.Li Zhengyun,Liu Yanwei,Wang Haixing.Analysis of water body extraction in Yanglin demonstration zone based on decision tree method [J].Journal of Water Resources & Water Engineering,2013,24(6):133-135.
[13] 朱海涛,张霞,王树东.基于面向对象决策树算法的半干旱地区遥感影像分类[J].遥感信息,2013,28(4):50-56.Zhu Haitao,Zhang Xia,Wang Shudong.Object-oriented and decision tree classification for remote sensing data in semi-arid areas [J].Remote Sensing Information,2013,28(4):50-56.
[14] 黄珊,林玮玮,王长连,等.基于决策树的万古霉素血药浓度解读及实践[J].中国药学杂志,2016,51(19):1710-1713.Huang Shan,Lin Weiwei,Wang Changlian,et al.Interpretation of vancomycin serum concentration based on decision tree and clinical practice [J].Chinese Pharmaceutical Journal,2016,51(19):1710-1713.
[15] 刘玥,张允岭,金香兰,等.基于决策树法缺血性脑卒中与短暂性脑缺血发作患者血瘀证识别模式比较研究[J].中华中医药杂志,2015,30(5):1723-1727.Liu Yue,Zhang Yunling,Jin Xianglan,et al.Comparison study of recognization patterns of ischemic stroke and TIA patients with blood stasis syndrome based on decision tree [J].China Journal of Traditional Chinese Medicine and Pharmacy,2015,30(5):1723-1727.
[16] 卢金锁,黄廷林,韩宏大,等.基于决策树技术及在线监测的水质预测[J].环境监测管理与技术,2006,18(2):38-41.Lu Jinsuo,Huang Tinglin,Han Hongda,et al.Forecast water quality based on decision-making tree and online monitoring [J].The Administration and Technique of Environmental Monitoring,2006,18(2):38-41.
[17] 曾勇,杨志锋,刘静玲.城市湖泊水华预警模型研究-以北京“六海”为例[J].水科学进展,2007,18(1):79-85.Zeng Yong,Yang Zhifeng,Liu Jingling.Algalbloom prediction models for Liuhai Lake in Beijing city [J].Advances in Water Science,2007,18(1):79-85.
[18] 唐国磊,周惠成,李宁宁,等.一种基于决策树技术的中长期径流分级方法[J].水力发电学报,2011,30(3):45-49.Tang Guolei,Zhou Huicheng,Li Ningning,et al.Medium-and-long-term runoff classification method using decision tree technique[J].Journal of Hydroelectric Engineering,2011,30(3):45-49.
[19] 张玮,杨善林,刘婷婷.基于CART和自适应Boosting算法的移动通信企业客户流失预测模型[J].中国管理科学,2014,22(10):90-96.Zhang Wei,Yang Shanlin,Liu Tingting.Customer churn prediction in mobile communication enterprises based on CART and boosting algorithm [J].Chinese Journal of Management Science,2014,22(10):90-96.
[20] 陈平,徐星.基于CART算法的带钢抗拉强度影响因素研究[J].控制工程,2015,22(2):276-281.Chen Ping,Xu Xing.Research of tensile strength of strip steel based on CART [J].Control Engineering of China,2015,22(2):276-281.
[21] 李春鑫,李天伟.基于决策树改进CART算法的决策支持与分析技术[J].计算机科学,2004,31(9A):44-46.Li Chunxin,Li Tianwei.Decision support and analysis technique based on improved CART arithmetic of decision tree [J].Computer Science,2004,31(9A):44-46.
[22] 张博,王书航,姜霞,等.丹江口库区土地利用格局与水质响应关系[J].环境科学研究,2016,29(9):1303-1310.Zhang Bo,Wang Shuhang,Jiang Xia,et al.Response relationship research between land use patterns and water quality in Danjiangkou Reservoir[J].Research of Environmental Science,2016,29(9):1303-1310.
[23] Merem E C,Yerramilli S,Twumasi Y A,et al.The applications of GIS in the analysis of the impacts of human activities on South Texas Watersheds [J].International Journal of Environmental Research and Public Health,2011,8(6):2418-2446.
[24] Su S,Zhi J,Lou L,et al.Spatio-temporal patterns and source apportionment of pollution in Qiantang River (China) using neural-based modeling and multivariate statistical techniques [J].Physics and Chemistry of the Earth,parts A/B/C,2011,36(9-11):379-386.
[25] Wang J,Da L,Song K,et al.Temporal variations of surface water quality in urban,suburban and rural areas during rapid urbanization in Shanghai,China [J].Environmental Pollution,2008,152(2):387-393.
[26] Chang H.Spatial analysis of water quality trends in the Han River basin,South Korea [J].Water Research,2008,13:3285-3304.
[27] 王国重,蔡崇法.磨沟小流域水土流失状况及对策[J].人民长江,2008,39(18):43-44.Wang Guozhong,Cai Chongfa.Soil and water loss condition of Mogou small basin and the countermeasures [J].Yangtze River,2008,39(18):43-44.
[28] 徐静,韩兆光.岳城水库饮用水源地水体富营养化预防措施探讨[J].海河水利,2011,(4):14-17,20.Xu Jing,Han Zhaoguang.The discussion on prevention measures of eutrophication in Yuecheng Reservoir drinking water source area [J].Haihe Water Resources,2011,(4):14-17,20.
[29] 王明浩,王文杰,冯宇,等.湖南水府庙水库流域景观格局与水质特征关系分析[J].环境工程技术学报,2015,5(4):333-340.Wang Minghao,Wang Wenjie,Feng Yu,et al.Relationship of landscape pattern and river water quality in Shuifumiao Reservoir watershed in Hunan Province [J].Journal of Environmental Engineering Technology,2015,5(4):333-340.
[30] 吉冬青,文雅,魏建兵,等.流溪河流域景观空间特征与河流水质的关联分析[J].生态学报,2015,35(2):246-253.Ji Dongqing,Wen Ya,Wei Jianbing,et al.Relationships between landscape spatial characteristics and surface water quality in the Liuxi River watershed [J].Acta Ecologica Sinica,2015,35(2):246-253.
[31] 张健,陈凤,濮励杰,等.经济快速增长区土地利用变化对土壤质量影响研究[J].环境科学研究,2007,20(5):99-104.Zhang Jian,Chen Feng,Pu Lijie,et al.The land use changes and its effects on the soil properties in the rapid developed region [J].Research of Environmental Sciences,2007,20(5):99-104.