摘要
将时间序列模型ARIMA和Prophet作为基学习器,结合BP神经网络模型构建了水质预测集成学习模型。选取长江流域某断面2019—2020年的DO、COD_(Mn)、NH_(3)-N、TP和TN等5个水质指标的监测数据对该模型的有效性进行了检验,结果表明:5个水质指标集成学习模型预测结果的平均绝对百分比误差比时间序列模型的预测误差分别低35.0%、29.9%、4.1%、40.6%和17.1%,模型预测值和监测值的皮尔逊相关系数大于0.8。集成学习模型预测精度高于单一模型,可以更精确地进行水质预测。
An ensemble learning model for water quality forecast was constructed by using time series models including ARIMA and Prophet model as base learners,combined with BP neural network model.The monitoring data of five water quality indicators,including DO,COD_(Mn),NH_(3)-N,TP and TN,for a section of the Yangtze River Basin from 2019 to 2020 were selected to test the validity of the model.The results show that the mean absolute percentage errors of the predicted results of the ensemble learning model for the five indicators were lower than those of the time series model by 35.0%,29.9%,4.1%,40.6%and 17.1%,respectively.The prediction accuracy of the ensemble learning model is higher than that of the single model,which can be more accurate for water quality forecast.
作者
嵇晓燕
杨凯
陈亚男
姚志鹏
王正
安新国
JI Xiaoyan;YANG Kai;CHEN Ya nan;YAO Zhipeng;WANG Zheng;AN Xinguo(China National Environmental Monitoring Center,Beijing 100012,China;Golden Water Technology(Beijing)Ltd.,Beijing 100012,China)
出处
《水资源保护》
EI
CAS
CSCD
北大核心
2022年第6期111-115,共5页
Water Resources Protection
基金
长江生态环境保护修复联合研究项目(2019-LHYJ-01-0301)
国家水环境监测监控及业务化平台技术研究课题(2017ZX07302002)。
