线性回归方法与MLP相结合预测李家河水库的综合水质指数  被引量:1

Prediction of comprehensive water quality index of Lijiahe Reservoir by combining linear regression method with MLP

在线阅读下载全文

作  者:杨玮伦 高宇轩 曹雷 Yang Weilun;Gao Yuxuan;Cao Lei(Xi'an Water(Group)Lijiahe Reservoir Management Co.,Ltd.,Xi'an 710082,Shaanxi;School of Computer Science and Engineering,Xi'an University of Technology,Xi'an 710048,Shaanxi)

机构地区:[1]西安水务(集团)李家河水库管理有限公司,陕西西安710082 [2]西安理工大学计算机科学与工程学院,陕西西安710048

出  处:《陕西水利》2023年第6期19-21,25,共4页Shaanxi Water Resources

摘  要:为了提高水库水质的监测和管理水平,提升对城市供水的质量,采用李家河水库2021全年实测的水质指标数据(每周测试一次),通过研究对比选择了七个重要指标(分别为:总氮、氨氮、总磷、高锰酸盐系数、总铁、总锰和溶解氧)作为自变量,将反映水库水质水平高低的综合水质指数(WQI)作为因变量,分别构建、训练得到了多元线性回归模型和MLP多层人工神经网络模型;并利用所建模型对2022年上半年水库的WQI进行预测,经与实测数据对比发现,将多元线性回归模型和MLP模型相结合预测的综合水质指数明显优于两个单独模型的预测结果,WQI变化趋势的预测准确率高达95.24%;本研究所获得的这一综合水质指数复合预测模型对于李家河水库后续水质监测和生产管理会起到有效的辅助作用,对于同类型中小水库也具有一定的推广借鉴价值。In order to improve the monitoring and management level of reservoir water quality and improve the quality of urban water supply,this paper adopts the water quality index data of Lijiahe Reservoir in 2021(tested once a week),selects seven important indexes(total nitrogen,ammonia nitrogen,total phosphorus,permanganate coefficient,total iron,total manganese and dissolved oxygen)as independent variables,and takes the comprehensive water quality index(WQI),which reflects the level of reservoir water quality,as dependent variables.The model was used to predict the WQI of the reservoir in the first half of 2022.Compared with the measured data,it was found that the comprehensive water quality index predicted by the combination of multiple linear regression model and MLP model was obviously better than the prediction results of two separate models,and the prediction accuracy of WQI change trend was as high as 95.24%.The comprehensive water quality index composite prediction model obtained in this study will play an effective auxiliary role in the follow-up water quality monitoring and production management of Lijiahe Reservoir,and also has certain popularization and reference value for small and medium-sized reservoirs of the same type.

关 键 词:李家河水库 线性回归模型 MLP神经网络模型 综合水质指标WQI 水质等级 

分 类 号:X524[环境科学与工程—环境工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象