Based On Bp Neural Network's Crops Pests Forecasting And Matlab Implementation

The main pests do serious harm to crops perennial and damage the agricultural economy. To predict the trends of pests in the future, the works to control the pests can be implemented designedly and purposefully. Only when the prediction is betimes and accurately, people can draw out the colligated plan and take the effective measure to reduce the quantity of pests and ensure agricultural product fruitful.The prediction of the occurrence level of pests is to predict the amount of pests and it is the core of which and how many fields need to be controlled. But the whole progress of the research is still behind the prediction of the occurrence time. It is because that there are too many effective factors, which are uncertain. So we propose a there-layer BP neural network that can better depict the model's feature of complex nonlinear, multi-input-output and indefinite.Neural network are composed of simple elements operating in parallel. These elements are inspired by biological nervous systems. As in nature, the network function is determined largely by connections (weights) between elements, so that a particular input leads to a specific target output.The cores of Backpropagation Neural Network are the capacity of parallel computing, distribute saving, self-studying, fault-tolerant and nonlinear function approximating. Input vectors and the corresponding target vectors are used to train a network until it can approximate a function, associate input vectors with specific output vectors, or classify input vectors in an appropriate way as defined by you.At present, during the course of BP neural network's learning and training, we often adopt the algorithm of back-error propagation, which is based on global error function's gradient descent. In order to solve the Bp neural network 's inherent deficiency of slowly converging and easily falling into local minimum, we propose to use an algorithm combined self-adapting learning rate and extra momentum. But, to establish BP network object, you must have rich program experiences, which hamper the development of neural networks in a way. An available Neural Network Toolbox (NNT) in MATLAB, however, solves the problem.In the thesis, how to use the backpropagation training functions in the MATLAB toolbox to train feedforward neural networks to solve specific problems is explained. Besides that,how to design the interface between MATLAB and DELPHI is presented.Through the thesis, we can see that it's easy and effective to make BP network objects by using the Neural Network Toolbox (NNT) based on MATLAB to evaluate the predictive model. The test that use the data of historical occurrence level of pests in paddy of Lujiang County, Anhui province is done, the result shows the feasibility of the predictive model. So it's valuable and has a bright future.