提出一种基于遗传算法的二类水体水色遥感反演算法。该算法以三成分 (叶绿素、悬浮泥沙与黄色物质 )海水光学模型作为前向模型 ,以实数编码遗传算法作为优化方法 ,并采用一对波段比来构造目标函数。模拟反演的结果表明 ,该算法可以有效克服已有二类水体水色遥感优化反演方法在搜索策略方面存在的困难 ,是一种有较高计算效率、可靠与稳健的反演算法。

The optimization approach is one of the most promising methods for retrieval of water constituents in case 2 waters,but almost previous applications of this approach suffer from their local search techniques. In this study, a genetic algorithm is developed as a global optimization scheme to simultaneously retrieve concentrations of chlorophyll, suspended sediment and yellow substance. To separate the contributions to the radiance spectra by co exiting constituents, two reflectance ratios were embodied to the objective function,and a real valued genetic algorithm was used to optimize it. The performance of the algorithm is demonstrated with a simulated data set. Under noise free conditions, three water constituents are estimated accurately. Tests with noisy data show that the algorithm is robust against errors in the reflectance data.