针对正则化方法在解决实际反演问题时既能克服问题的不适定性又可以很大程度上抑制噪声和误差的传播,本文提出了利用遗传算法结合正则化方法的新算法,在遗传算法适应度函数中引入正则化项来反演波导参数;然后对算法进行仿真试验,结果表明新算法与传统遗传算法相比具有较高的反演精度,并指出当噪声误差小于10%时,算法具有较强的“去噪”性能;最后利用机载雷达在Wallops岛探测的海表面处局部回波资料进行反演试验,将反演结果与实测大气折射率廓线进行比较,说明该算法的有效性.新方法为海洋大气波导反演研究提供了一种新思路. The regularization method can not only overcome the ill-posedness of the problem but also suppress the propagation of noise and error to a large extent when solving the actual inversion problem. In this paper, we propose a new genetic algorithm combined with regularization method, The regularization term is introduced into the function to invert the waveguide parameters. Then the simulation experiment is carried out. The results show that the new algorithm has higher inversion accuracy compared with the traditional genetic algorithm, and points out that when the noise error is less than 10% Strong “denoising” performance. Finally, using the local echo data of airborne radar at the sea surface detected by Wallops Island, the inversion results are compared with the measured atmospheric refractive index profiles. Validity.The new method provides a new idea for the research of marine atmospheric waveguide inversion.