Taking the evaluation criterion of lake nutrient states as sample pattern, the network was trained in the light of learning rule of Error Back Propagation network.

• 将湖泊营养状态评价标准作为样本模式提供给网络，按照误差逆传播网络的学习规则对网络进行训练，经过39925次学习后，网络达到预先给定的收敛标准。