PDF Download

[1]BIAN Jian-min,HU Yu-xin,LI Yu-song,et al.Water Quality Assessment in Source Area of Liao River Based on BP Neural Network[J].Research of Soil and Water Conservation,2014,21(01):147-151.

Copy

Water Quality Assessment in Source Area of Liao River Based on BP Neural Network

Research of Soil and Water Conservation[ISSN 1005-3409/CN 61-1272/P] Volume: 21 Number of periods: 2014 01 Page number: 147-151 Column: Public date: 2014-02-28

Title:: Water Quality Assessment in Source Area of Liao River Based on BP Neural Network

Author(s):: BIAN Jian-min¹, HU Yu-xin¹, LI Yu-song¹, MA Yong-xiang², BIAN Jing³; 1. College of Environment and Resources, Jilin University, Changchun 130021, China;
2. Ningxia Hui Autonomous Region Bureau of Coal Geological Exploration, Yinchuan 750004, China;
3. Geo-Environmental Monitoring Central Station of Jilin Province, Changchun 130021, China

Keywords:: source area of Liao River; BP neural network; network training; water quality assessment

CLC:: X524;TP183

DOI:: -

Abstract:: Based on the present situation that the water environmental issues in source area of Liao River have become increasingly prominent, the research for water environment quality was carried out to evaluate and analyze the regional water quality. Through data collection and summary, a comprehensive water quality evaluation model was established based on the thought and theory of BP artificial neural network with including pH, DO, ammonia nitrogen, COD, BOD₅, potassium permanganate index, and finished with water quality monitoring data of the 13 sections in the study area. After training well, it can just be applied in model simulating operation and water quality comprehensive evaluation. The results have showed that in the selected sections, approximately 76.92% of the sections are between class V and worse than class V, leaving only 23.08% of the sections whose water quality levels are between class Ⅱand class Ⅲ in the selected 13 sections. The sections located in the upper reaches have a better water quality than that in the downstream. Compared the evaluation results with the results of main sections published in Environment Communique, 81.25% of the evaluation results are identical. It has strong applicability and reliability that BP neural network was used to comprehensively evaluate water quality in the study area.

References:: [1] 张利静,余麟,刘红琴,等.辽河源头区跨界污染输入响应模型的建立[J].科学技术与工程,2012,12(23):5952-5955.
[2] 葛淑芳.辽河吉林省段水环境容量研究[D].长春:吉林大学,2012.
[3] 马溪平,吕晓飞,张利红,等.辽河流域水质现状评价及其污染源解析[J].水资源保护,2011,27(4):1-4.
[4] 孙维.基于GIS的辽河源头区地表水评价研究[D].长春:吉林大学,2011.
[5] 郭华.不同评价法在清河水质评价中的应用[J].人民长江,2012,43(1):132-134.
[6] 鲁斐,李磊.主成分分析法在辽河水质评价中的应用[J].水利科技与经济,2006,12(10):660-662.
[7] 侯淑艳,曲晓晶,刘建新,等.基于综合评价法的天津市主要排污河流水质评价[J].水土保持研究,2011,18(4):61-64.
[8] 周林飞,赵崭,孙佳竹,等.基于模糊模式识别的浑河水质评价研究[J].水土保持研究,2012,19(5):163-166.
[9] 刘登峰,齐实,韩小杰,等.缙云山不同土地利用类型地表径流水质评价[J].水土保持研究,2009,16(1):126-130.
[10] 郭庆春,何振芳,李力,等.BP神经网络在渭河水环境质量评价中的应用[J].水土保持通报,2011,31(4):112-115.
[11] 张丽,吴金亮,杨国范.基于BP神经网络的东港灌区作物需水量预测研究[J].水土保持研究,2012,19(6):207-211.
[12] 许秀英,黄操军,杨秋梦,等.基于遗传神经网络的黑龙江浅表地层水分预测[J].水土保持研究,2013,20(1):269-272.
[13] 杜富芝,傅瓦利,杜小红,等.基于BP神经网络的三峡库区小流域水质评价[J].节水灌溉,2009(1):8-10.
[14] 陈东彦.数学建模[M].北京:科学出版社,2007.
[15] 杨芳,原松.基于BP神经网络的水环境质量评价模型的研建[J].人民长江,2008,39(23):46-48.
[16] 马莉.MATLAB数学实验与建模[M].北京:清华大学出版社,2010.
[17] 杨洁,吴贻名,万飚,等.汉江水质综合评价的BP网络方法[J].武汉大学学报:工学版,2004,37(1):51-54.
[18] 王李,刘志斌,常欢.水质评价的BP神经网络应用[C]//第三届全国农业环境科学学术研讨会论文集.2009.
[19] 王庚,王敏生.现代数学建模方法[M].北京:科学出版社,2008.
[20] 楼文高,王延政.基于BP网络的水质综合评价模型及其应用[J].环境污染治理技术与设备,2003,4(8):23-26.

Similar References:

Memo

Last Update: 1900-01-01