为了提升我国SAR图像应用的基础支撑能力，各方均认为应该建设完备的SAR目标特性库。目前，基于电磁建模仿真构建SAR目标特性库图像的准确性依赖于地物仿真参数，仿真参数难以通过理论获取。针对这个问题提出了一种基于卷积神经网络的SAR图像最佳仿真参数预测方法。该方法将仿真获取的SAR仿真图像作为输入，建立了一个11层的卷积神经网络回归系统。因为预测的仿真参数是4维，提出了一种新的损失函数来解决多维回归中的每个维度预测的准确性问题。通过对神经网络训练时参数的误差幅值变化分析，可以看到该损失函数在4维的预测上都能取得比较好的效果;通过对真实图像和仿真图像的对比，可以看到真实图像和仿真图像具有很高的相似性，验证了该方法的有效性。

It is widely agreed that a complete Synthetic Aperture Radar (SAR) target feature library should be built to improve the basic support capability of SAR image applications in China.At presentthe accuracy of the SAR image in the SAR target feature library built by the electromagnetic modeling simulation depends on the simulation parameters of the ground object.The simulation parameters can hardly be obtained by theory.To solve this problema method based on Convolutional Neural Network (CNN) is proposed to predict the best simulation parameters of SAR images.An 11-layer CNN regression system is builtwhose input is the SAR simulation image.Since the predicted simulation parameters are 4 dimensional a new loss function is proposed to improve the predicted accuracy of each dimension in the process of multidimensional regression.Through an analysis of the changes in the error amplitude of the parameters during the training of the neural networkit can be seen that the loss function can achieve the desired result in the prediction of all the 4 dimensions.A comparison between the real image and the simulated image shows a high similarity between themwhich validates the effectiveness of this method.