Water quality forecast through application of BP neural network at Yuqiao reservoir

This paper deals with the study of a water quality forecast model through application of BP neural network technique and GUI (Graphical User Interfaces) function of MATLAB at Yuqiao reservoir in Tianjin. To overcome the shortcomings of traditional BP algorithm as being slow to converge and easy to reach extreme minimum value,the model adopts LM (Leven-berg-Marquardt) algorithm to achieve a higher speed and a lower error rate. When factors affecting the study object are identified,the reservoir's 2005 measured values are used as sample data to test the model. The number of neurons and the type of transfer functions in the hidden layer of the neural network are changed from time to time to achieve the best forecast results. Through simulation testing the model shows high efficiency in forecasting the water quality of the reservoir.

Application of a Neural Network Technique for Prediction of the Water Quality Index in the Dong Nai River, Vietnam

Recent trends in environmental management of water resource have enlarged the demand for predicting techniques that can provide reliable, efficient and accurate water quality. In this case study, the authors applied the Artificial Neural Networks （ANN） to estimate the water quality index on the Dong Nai River flowing through Dong Nai and Binh Duong provinces. The information and data including 10 water quality parameters of the Dong Nai River at 23 monitoring stations were collected during the recorded time period from 2010 to 2014 to build water quality prediction models. The results of the study demonstrated that the Water Quality Index （WQI） forecasted with GRNN was very significant and had high correlation coefficient （R2 = 0.974 and p = 0.0） compared to the real values of the WQI. Moreover, the ANN models provided better predicted values than the multiple regression models did.

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

In the present study, ELMAN artificial neural network model was developed to predict the change of NH3-N in aquaculture water. The in- dexes including feed ration, dissolved oxygen in water, water temperature, air temperature, water turbidity, rainfall were recorded and chosen as the input variables, while the NHz-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 accu- racy in practical application.

Determination of the principal factors of river water quality through cluster analysis method and its prediction

In this paper, an artificial neural network model was built to predict the Chemical Oxygen Demand （CODMn） measured by permanganate index in Songhua River. To enhance the prediction accuracy, principal factors were determined through the analysis of the weight relation between influencing factors and forecasting object using cluster analysis method, which optimized the topological structure of the prediction model input items of the artificial neural network. It was shown that application of the principal factors in water quality prediction model can improve its forecasting skill significantly through the comparison between results of prediction by artificial neural network and the measurements of the CODMn. This methodology is also applicable to various water quality prediction targets of other water bodies and it is valuable for theoretical study and practical application.

Forecasting of dissolved oxygen in the Guanting reservoir using an optimized NGBM(1,1) model

An optimized nonlinear grey Bernoulli model was proposed by using a particle swarm optimization algorithm to solve the parameter optimization problem. In addition, each item in the first-order accumulated generating sequence was set in turn as an initial condition to determine which alternative would yield the highest forecasting accuracy. To test the forecasting performance, the optimized models with different initial conditions were then used to simulate dissolved oxygen concentrations in the Guantlng reservoir inlet and outlet （China）. The empirical results show that the optimized model can remarkably improve forecasting accuracy, and the particle swarm optimization technique is a good tool to solve parameter optimization problems. What＇s more, the optimized model with an initial condition that performs well in in-sample simulation may not do as well as in out-of-sample forecasting.