Establishment of NH_3-N Prediction Model in Aquaculture Water Based on ELMAN Neural Network

• 作 者: Wang Xiang He Jixiang She Lei Zhang Jing
• 机 构: Fisheries Research Institute,Anhui Academy of Agricultural Sciences,
• 出 处: Meteorological and Environmental Research
• 发表日期: 2015年10期
• 关键词: aquaculture Prediction dissolved ammonia adaptability absolute everyday chosen r

In the present study,ELMAN artificial neural network model was developed to predict the change of NH3-N in aquaculture water. The indexes including feed ration,dissolved oxygen in water,water temperature,air temperature,water turbidity,rainfall were recorded and chosen as the input variables,while the NH3-N content in the corresponding pond was chosen as output variable. The above data were collected everyday from June to October in 2014 and were used to develop model in this test,and the data collected in November of 2014 were chosen to evaluate the developed model. The results showed that the changing trend of NH3-N in aquaculture water could be simulated well by the model,the predictive absolute error mean was 0. 016 mg / L,and Nash-Sutcliffe efficiency coefficient was 0. 74. The prediction model based on ELMAN neural network had a strong ability to describe the nonlinear dynamic changes of NH3-N content in aquaculture water,and it showed the good adaptability and accuracy in practical application.

In the present study, ELMAN artificial neural network model was developed to predict the change of NH3-N in aquaculture water. The Index includes feed ration, dissolved oxygen in water, water temperature, air temperature, water turbidity, rainfall were recorded and chosen as the input variables, while the NH3-N content in the corresponding pond was chosen as output variable. The above data were collected everyday from June to October in 2014 and were used to develop model in this test, and the data collected in November of 2014 The chosen was evaluated to the developed model. The results showed that the changing trend of NH3-N in aquaculture water could be simulated well by the model, the predictive absolute error mean was 0. 016 mg / L, and Nash-Sutcliffe efficiency coefficient was 0. 74. The prediction model based on ELMAN neural network had a strong ability to describe the nonlinear dynamic changes of NH3-N content in aquaculture water, and it showed the good adaptability and accuracy in practi cal application.