基于Sentinel-2卫星和优化RBF模型反演香港海域叶绿素a浓度OA北大核心CSCDCSTPCD
Inversion of chlorophyll a concentration in Hong Kong waters based on Sentinel-2 satellite and optimized RBF model
叶绿素 a 浓度是评估水质状况的重要参数之一,然而因为近海的二类水体光谱特征复杂,影响了其中叶绿素 a 浓度反演的可靠性.本文提出了一种动态 K-means 聚类与粒子群最优化算法(Particle Swarm Optimization,PSO)优化的径向基神经网络反演模型,用以提高叶绿素 a 浓度反演的精度.以Sentinel-2 多光谱成像仪作为遥感数据源,选择与香港近海的叶绿素 a 浓度监测点时间相同、云覆盖率低于 10%的遥感影像,并提取对应叶绿素 a 浓度监测点的遥感反射率,并与其进行相关性分析.在此基础上,选择具有较高相关性的波段及波段组合 B2、1/B2、1/B3、B2-B4,构建优化后的 RBF 模型,并与传统经验模型和传统 RBF 模型作为比较.结果表明:优化的 RBF 模型决定系数为 0.90,均方根误差为 0.23 μg·L-1,两种算法优化后的 RBF 模型对近海二类水体中叶绿素 a 浓度反演的可靠性远远高于传统经验模型和传统 RBF 模型.同时反演结果显示香港近海海域叶绿素 a 浓度从西到东呈现低-高-低的空间分布,局部上呈现近岸高、外海逐渐降低的特征.
Chlorophyll-a concentration is a crucial parameter for the aquatic environment.However,because of the complexity of the spectral characteristics of offshore Case-Ⅱ water,which affects the reliability of the inversion of chlorophyll-a concentration in them.To assess the suitability of the radial basis function(RBF)neural network,enhanced by the dynamic K-means clustering and particles swarm optimization,for chlorophyll-a concentration inversion in Case-Ⅱ water,Sentinel-2 multispectral image remote sensing data were employed.Hong Kong offshore served as the study area.Sampling points with matching remote sensing image data were chosen based on consistent chlorophyll-a collection times,ensuring cloud coverage rates below 10%.Remote sensing image data underwent preprocessing to obtain reflectance values aligned with the monitoring dates.On this basis,bands with high corre-lation and their combinations B2,1/B2,1/B3 and B2-B4 were selected to construct the optimized RBF model,and compared with the traditional empirical model and the traditional RBF model.Results indicated an R2 value of 0.90 for the optimized RBF model,surpassing the traditional RBF models and empirical models.Additionally,the opti-mized RBF model's suitability for chlorophyll-a concentration inversion in Case-Ⅱ water was confirmed.Using the trained and optimized RBF model,chlorophyll-a concentration inversion in Hong Kong's offshore waters was exe-cuted using Sentinel-2 MSI data.The spatial distribution exhibited a pattern of low-high-low from west to east.Notably,certain areas within Hong Kong offshore waters displayed higher chlorophyll-a concentrations compared to the surrounding external waters.
张磊;赵宽;魏来;管守德;赵玮
海南省海洋立体观测与信息重点实验室,中国海洋大学三亚海洋研究院,海南 三亚 572024海南省海洋立体观测与信息重点实验室,中国海洋大学三亚海洋研究院,海南 三亚 572024海南省海洋立体观测与信息重点实验室,中国海洋大学三亚海洋研究院,海南 三亚 572024海南省海洋立体观测与信息重点实验室,中国海洋大学三亚海洋研究院,海南 三亚 572024||物理海洋教育部重点实验室,山东 青岛 266100海南省海洋立体观测与信息重点实验室,中国海洋大学三亚海洋研究院,海南 三亚 572024||物理海洋教育部重点实验室,山东 青岛 266100
资源环境
叶绿素a浓度RBF神经网络动态K-means聚类粒子群最优化算法香港近海
chlorophyll-a concentrationRBF neural networkdynamic K-means clustering algorithmparticle swarm optimi-zationHong Kong offshore waters
《海洋科学》 2025 (10)
1-13,13
国家重点研发计划项目(2022YFD2401304) the National Key R&D Program of China,No.2022YFD2401304
评论