基于神经网络的扎龙湿地土地覆盖分类研究

主要研究神经网络在土地覆盖分类方面的应用问题．采用四层神经网络结构，对扎龙湿地的TM影像进行了分类研究，并提出一种基于鲁棒误差函数的自适应反向传播学习算法．仿真结果表明，该方法能够有效地对扎龙湿地TM影像进行分类．所采用的四层网络结构可减轻存储量大的负担，鲁棒误差函数有效地抑制了大误差，自适应反向传播算法使误差下降更快，而且最终得到的分类精度高于三层神经网络和最大似然法的分类精度。

Research on classification of land cover in Zhalong wetland area based on neural network

Neural network is applied to the classification of land cover. An adaptive back-propagation algorithm based on a robust error function is introduced to build a four-layer neural network, and it is used to classify TM image of Zhalong wetland. Comparing the classification results of the four-layer neural network with those of the three-layer neural network and the maximum likelihood classifier, conclusions can be drawn as follows: the structure of the four-layer neural network and the adaptive back-propagation algorithm based on the robust error function is effective to classify the TM image data. The four-layer neural network adopted in this paper can succeed in building the complex model of TM image, and it avoids the problem of the great storage of data. The robust error function avoids the great error and the adaptive back-propagation algorithm speeds up the descending of the error. Above all, the four-layer neural network is superior to the three-layer neural network and the maximum likelihood classifier in the accuracy of the classification.