改进鲸鱼优化算法的叶片生化参数反演  

Biochemical Parameters Inversion of Leaf by Improved Whale Optimization Algorithm

作　　者：时鸣 竞霞[1] SHI Ming;JING Xia(College of Geomatics,Xi’an University of Science and Technology,Xi’an 710054,China)

机构地区：[1]西安科技大学测绘科学与技术学院,陕西西安710054

出　　处：《地理空间信息》2023年第5期1-4,共4页Geospatial Information

基　　金：国家自然科学基金面上项目(42171394);国家自然科学基金青年基金资助项目(41601467)。

摘　　要：为提高植被叶片生化参数的反演精度,利用扩展傅里叶幅度敏感性检验法对阔叶辐射传输模型进行敏感性分析,提取了叶绿素、类胡萝卜素、水分和干物质对应的敏感波段。在鲸鱼优化算法的基础上,引入改进的混沌序列对种群进行初始化,产生分布均匀的个体;再引入非线性收敛因子与权重对鲸鱼优化算法参数进行改进,并利用改进后的参数对个体位置进行更新,使算法更易遍历全局寻找最优解;然后在一次迭代完成时对适应度进行排序,选出适应度高的精英个体,通过扰动概率对精英个体进行高斯扰动,增加算法跃出局部最优的概率,形成改进鲸鱼优化算法;最后与粒子群优化算法的反演精度进行比较。结果表明,改进鲸鱼优化算法反演的叶绿素、类胡萝卜素和等效水厚度的精度均高于粒子群优化算法;其算法与分波段反演模型对生化参数的预测精度更高,可为定量预测植被叶片生化组分含量提供一定的理论和技术支持。In order to improve the accuracy of leaf biochemical parameters inversion,we used the extended Fourier amplitude sensitivity test to carry out the sensitivity analysis of broad-leaf radiative transfer model,and extracted the sensitive bands of chlorophyll,carotenoid,water and dry matter.Based on the whale optimization algorithm(WOA),we introduced the improved chaotic sequence to initialize the population and produce uniformly distributed individuals at first.Then,we introduced the nonlinear convergence factor and weight to improve the parameters of WOA,and used the improved parameters to update individual positions,making the algorithm easier to traverse the whole world to find the optimal solution.We sorted the fitness values at the completion of iteration,and selected elite individuals with high fitness.We performed Gaussian perturbation on elite individuals through perturbation probability to increase the probability of algorithm jumping out of the local optimal,and formed improved whale optimization algorithm(IWOA).Finally,we compared the inversion accuracy of IWOA with that of the particle swarm optimization algorithm.The results show that the accuracy of chlorophyll,carotenoid and equivalent water thickness inversion by IWOA is higher than that by particle swarm optimization algorithm.This algorithm and band inversion model can predict biochemical parameters with higher accuracy,which can provide certain theoretical and technical support for quantitative prediction of biochemical components content in vegetation leaves.

关 键 词：鲸鱼优化算法 辐射传输 生化组分 叶片 

分 类 号：P237[天文地球—摄影测量与遥感]