BP神经网络在焉耆盆地农田排水量估算中的应用

We try to use BP neural network to estimate the farm drainage in the Yanqi Basin. The correlation between drainage and the influencing factors was estimated by gray correlation degree. The five most important influencing factors were chosen to construct the BP neural network to estimate the drainage. To ascertain the best structure of BP neural network, the uniform design was used. The results of estimation show that BP neural network can estimate farmland drainage accurately and the largest relative error is only –2.45%.