Water Quality Forecast Based on BP-Artificial Neural Network Model in Qiantang River

Applied Mechanics and Materials(2014)

引用 0|浏览0
暂无评分
摘要
This study aims at providing a back propagation-artificial neural network (BP-ANN) model on forecasting the water quality change trend of Qiantang River basin. To achieve this goal, a three-layer (one input layer, one hidden layer, and one output layer) BP-ANN with the LM regularization training algorithm was used. Water quality variables such as pH value, dissolved oxygen, permanganate index and ammonia-nitrogen was selected as the input data to obtain the output of the neural network. The ANN structure with 17 hidden neurons obtained the best selection. The comparison between the original measured and forecast values of the ANN model shows that the relative errors, with a few exceptions, were lower than 9%. The results indicated that the BP neural network can be satisfactorily applied to forecast precise water quality parameters and is suitable for pre-alarm of water quality trend.
更多
查看译文
关键词
artificial neural network,Qiantang River,water quality forecast,model
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要