Abstract: A prediction model of underground water level that combined ant colony algorithms with radial basis function neural network is proposed.It not only has extensive mapping ability of neural network，but aslo has the advantages of global covergence and distributed computation of ant system.The experimental result indicates good performance can be obtained by neural network based on ant colony algorithms in prediction of underground water level.

Key words: ant colony algorithms, radial basis function network, underground water level, prediction

摘要： 提出了一种基于蚁群算法的径向基函数神经网络，用它来进行地下水位预测，既具有神经网络广泛映射能力，又具有蚁群算法全局寻优、分布式计算等特点。实验表明，蚁群算法与径向基函数神经网络相融合能达到良好的预测效果。

关键词: 蚁群算法, 径向基函数网络, 地下水位, 预测