A hybrid algorithm of the BP-ANN/GA (Back Propagation Artificial Neural Network and Genetic Algorithm) is developed to optimize the initial weights and make fast convergence of the BP-ANN. This algorithm is applied to classification of urban terrain surfaces with fused data of Landsat ETM+ and ERS-2 SAR. An example of the Shanghai Pudong area using both the Landsat ETM+ and ERS-2 SAR image data well demonstrates the classification speed and accuracy of the algorithm.