长江流域资源与环境 >> 2014, Vol. 23 >> Issue (02): 260-.doi: 10.11870/cjlyzyyhj201402015

• 生态环境 • 上一篇    下一篇

多重组合神经网络模型在湖库总磷预测中的应用研究

崔东文   

  1. (云南省文山州水务局,云南 文山 663000)
  • 出版日期:2014-02-20

APPLICATION OF MULTIPLE NEURAL NETWORK MODEL IN THE PREDICTION OF TOTAL PHOSPHORUS IN LAKE AND RESERVOIR 

CUI Dongwen   

  1. (Yunnan Water Resources Bureau of Wenshan Prefecture of Yunnan Province,Wenshan 663000,China)
  • Online:2014-02-20

摘要:

湖库总磷(TP)含量与环境因子的相关性往往并不显著,导致总磷预测精度不高,效果不理想。为提高总磷的预测精度,提出一种基于BP、Elman、RBF、GRNN(以下简称BP等4种)神经网络算法原理的组合预测模型,将影响总磷预测精度的NH+4N、CODMn和透明度3个相关因子作为BP等4种模型的输入向量,总磷实测值作为输出向量,构建3输入1输出的单一预测模型;以BP等4种单一模型预测结果作为下一BP等4种模型的输入向量,总磷实测值作为输出向量,从而构建4输入1输出的一次组合预测模型;再以一次组合神经网络模型预测结果作为下一BP等4种模型的输入向量,总磷实测值作为输出向量,构建4输入1输出的二次组合预测模型;依次类推,构建8种方案的多重组合预测模型。并构建GABP模型作为对比预测模型,预测结果与BP等4种单一模型及GABP模型的预测结果进行比较。结果表明:(1)组合模型随着组合重数的增加,预测精度显著提高,表明多重组合模型用于湖库总磷预测是合理可行的,模型具有较好的预测精度和泛化能力,是提高预测精度的有效方法;(2)方案2~8中各模型的预测结果均优于GABP模型(除方案2中的GRNN外),表明组合模型具有较高的预测精度和泛化能力。其中,方案3中的BP模型、方案4~8中的BP、Elman和RBF模型的平均相对误差均小于10%,预测精度均令人满意,尤以方案6~8中的BP、Elman和RBF模型的预测精度为最高(平均相对误差均在9%以内),均优于其他组合模型

Abstract:

Total phosphorus (TP) concentration has often been found to do not correlate significantly to other environmental factors,leading to a low prediction accuracy of total phosphorus.In order to improve the prediction accuracy of total phosphorus,we proposed neural network algorithm combined forecasting models  based on  BP,Elman,RBF,GRNN (simplied as BP 4 in the following).Setting the three related factors,i.e.NH+4N,CODMn and transparency  as the input and the measured values as the output,a single forecasting model of 3 input and 1 output was established.Then,using the output of BP 4 single model as the input of next BP 4 model,and total measured values as output,a combination forecasting model with 4 input and 1 output was established; taking this procedure once more and a secondary combination forecasting model with 4 input and 1 output was established,being followed by  construction of 8 schemes of multiple combination forecasting model.The results showed as follows.In the combination models,the prediction accuracy is remarkably increased with increasing weight number of combination,indicating that multiple combination model for lake total phosphorus prediction is reasonable and feasible,and that the model has higher prediction accuracy and generalization ability,and it is the effective method to improve the prediction accuracy.All the predicted results from scheme 2 to scheme 8 were better than that from the GABP model (except for 2 GRNN),indicating that the combination model has high forecasting accuracy and generalization ability.Among them,the average relative error of BP model in scheme 3,plan 4-8 in BP,Elman and RBF model was less than 10%,demonstrating that the prediction accuracy is satisfactory.In the programme from 6 to 8,BP,Elman and RBF model,prediction accuracy is the highest (average relative errors are within 9%),being better than other combination model

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 李崇明,黄真理. 三峡水库入库污染负荷研究(Ⅱ)——蓄水后污染负荷预测[J]. 长江流域资源与环境, 2006, 15(1): 97 -106 .
[2] 张 政, 付融冰| 杨海真, 顾国维. 水量衡算条件下人工湿地对有机物的去除[J]. 长江流域资源与环境, 2007, 16(3): 363 .
[3] 李 佳,李思悦,谭 香,张全发. 南水北调中线工程总干渠沿线经过河流水质评价[J]. 长江流域资源与环境, 2008, 17(5): 693 .
[4] 邹丽敏, 王 超, 冯士龙. 玄武湖沉积物中重金属污染的潜在生物毒性风险评价[J]. 长江流域资源与环境, 2008, 17(2): 280 .
[5] 许素芳,周寅康. 开发区土地利用的可持续性评价及实践研究——以芜湖经济技术开发区为例[J]. 长江流域资源与环境, 2006, 15(4): 453 -457 .
[6] 郝汉舟, 靳孟贵, 曹李靖, 谢先军. 模糊数学在水质综合评价中的应用[J]. 长江流域资源与环境, 2006, 15(Sup1): 83 -87 .
[7] 刘耀彬, 李仁东. 现阶段湖北省经济发展的地域差异分析[J]. 长江流域资源与环境, 2004, 13(1): 12 -17 .
[8] 陈永柏,. 三峡工程对长江流域可持续发展的影响[J]. 长江流域资源与环境, 2004, 13(2): 109 -113 .
[9] 陈 爽,王 进,. 太湖流域城市化水平及外来人口影响测评[J]. 长江流域资源与环境, 2004, 13(6): 524 -529 .
[10] 翁君山,段 宁| 张 颖. 嘉兴双桥农场大气颗粒物的物理化学特征[J]. 长江流域资源与环境, 2008, 17(1): 129 .