Identification and evaluation of oil and gas reservoirs is an essential part in the work of oil exploration and development. Generally speaking, the existing lithology identification methods can't be expressed in formation heterogeneity, the impact of layer parameters varies with depth arising is not taken into account. This paper presents a model of lithologic identification based on radial basis process neural network, which is verified by the actual data. The experimental result shows that the proposed method has a high recognition rate, and it is a practical application method.