Application of Artificial Neural Network in the Prediction of Output in Oilfield

In view of the problem that it is difficult to predict the output in an oilfield which affected by multiple variables, a backpropagation (BP) neural network model is built to predict the output in oilfield because the classic statistical method and static model can not meet the demand of precision for the nonlinear and uncertain system. Effective depth, permeability, porosity and water content are used as the input of neural network and oilfield output as the output of the neural network. The results show that this prediction approach is very effective and has higher accuracy. The results show that the model can forecast the oilfield output with accuracy comparable to other classic methods. So the BP neural network is an effective method to predict the oilfield output with high accuracy. The application of this approach can supply reliable data for the development of oilfield and decrease the risks for the exploitation.