Abstract:  A BP neural network model for the evaluation of water resources carrying capacity is established in line with pattern recognition of neural network as well as the evaluation indexes and criteria. The model aims to evaluate and analyze the carrying capacity of water resources in different target years with different reliabilities. It's found that the carrying capacity of water resources neither in Wenshan prefecture nor its administrative counties reaches the I-level, which suggests that the water resources in these regions are still capable of being exploited. The evaluation results are clear, and are consistent with the reality in these regions. It could be applied to the comprehensive evaluation of regional water resources carrying capacity.

Key words: carrying capacity of water resources, BP neural network, comprehensive evaluation, Wenshan Prefecture