| 用TM图象估算海表面叶绿素浓度的神经网络模型 |
| |
| 引用本文： | 赵冬至,张丰收,赵玲,丛丕福,曲元.用TM图象估算海表面叶绿素浓度的神经网络模型[J].海洋环境科学,2001,20(1):16-21. |
| |
| 作者姓名： | 赵冬至 张丰收 赵玲 丛丕福 曲元 |
| |
| 作者单位： | 1. 国家 海洋环境监测中心,
2. 大连海事大学 环境科学与工程学院, |
| |
| 基金项目： | 国防科学技术工业委员会资助项目(Y96-11) |
| |
| 摘 要： | 叶绿素浓度是衡量海洋水体质量的重要参数之一。本文以大连湾为示范区于1999年5月10日进行了现场卫星同步实验，采用神经网络模型技术模拟了TM1、TM2两个波段的辐射亮度值与在该湾海域现场获得的叶绿素浓度数据之间的传递机理。结果表明，使用TM图象的两人可见光波段作为输入，采用两层神经网络结构能建立比多回归分析更高的海水表层叶绿素浓度模型。回归分析的相关系数为0.49，神经网络分析的相关系数为0.87.
|
| 关 键 词： | TM图像 叶绿素浓度 神经网络 模型 海洋水体质量 |
| 文章编号： | 1007-6336(2001)01-0016-06 |
| 修稿时间： | 2000年3月17日 |
A neural network model for estimating sea surface chlorophyll from thematic m apper imagery |
| |
| ZHAO Dong-zhi,ZHANG Feng-shou,ZHAO Ling,CONG Pei-fu,QU Yuan.A neural network model for estimating sea surface chlorophyll from thematic m apper imagery[J].Marine Environmental Science,2001,20(1):16-21. |
| |
| Authors: | ZHAO Dong-zhi ZHANG Feng-shou ZHAO Ling CONG Pei-fu QU Yuan |
| |
| Abstract: | One of important parameters used for monitoring coastal water quality is the concentration of chlorophyll in surface water. Ocean color remote sensing provides a convenient method to determine this concentration from upwelling radiance. In the open ocean, it is not difficult to derive statistics model relating imagery radiance to surface concentrations of chlorophyll. However, in turbid coastal waters, due to the presence of suspended sediment and dissolved material, the spectral signal of chlorophyll was overwhelmed. Here, a neural network method was used to derive successful concentration of chlorophyll model relating received radiance from TM1 and TM2 of LANDSAT to synchronous data in situ in the Dalian Bay,which have a much higher accuracy than regression analysis. |
| |
| Keywords: | Thematic Mapper concentration of chlorophyll neural network model |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
