| 神经网络反演散射计风场算法的研究 |
| |
| 引用本文： | 宋新改,林明森,蒋兴伟. 神经网络反演散射计风场算法的研究[J]. 海洋学报, 2006, 28(1): 42-46 |
| |
| 作者姓名： | 宋新改 林明森 蒋兴伟 |
| |
| 作者单位： | 中国海洋大学,山东,青岛,266003;中国海洋大学,山东,青岛,266003;国家卫星海洋应用中心,北京,100081;国家卫星海洋应用中心,北京,100081 |
| |
| 摘 要： | 建立了一个神经网络反演卫星散射计海面风场的B-P算法,给出了一个神经网络反演风场的模型,并利用该反演算法和模型对实际卫星散射计数据进行了海面风场反演试验,对风向的多解性利用圆中数滤波方法进行排除.对神经网络训练和检验数据集分别采用ERS-1/2散射计数据和欧洲中期天气预报(ECMWF)提供的风场作为配准点数据.把反演的风速和风向与CMCD4和ECMWF的风场作了比较,它们吻合得比较好;研究表明神经网络反演海面风场是可行和高效的.
|
| 关 键 词： | B-P网络 散射计 风场反演 模糊消除 |
| 文章编号： | 0253-4193（2006）01-0042-05 |
| 收稿时间： | 2005-04-15 |
| 修稿时间： | 2005-04-152005-08-18 |
Neural network wind retrieval from ERS-1/2 scatterometer data |
| |
| SONG Xin-gai,LIN Ming-sen and JIANG Xing-wei. Neural network wind retrieval from ERS-1/2 scatterometer data[J]. Acta Oceanologica Sinica (in Chinese), 2006, 28(1): 42-46 |
| |
| Authors: | SONG Xin-gai LIN Ming-sen JIANG Xing-wei |
| |
| Affiliation: | 1.Ocean University of China, Qingdao 266003 China2.Ocean University of China, Qingdao 266003 China;National Satellite Ocean Application Service, Beijing 100081, China3.National Satellite Ocean Application Service, Beijing 100081, China |
| |
| Abstract: | A neural network methodology is presented to retrieve wind vectors from ERS-1/2 scatterometer data,and resolving directional ambiguities for scatterometer winds are removed by a circular median filter algorithm.Training data set and test data set come from ERS-1/2 scatterometer data collocated pairs with ECMWF vectors.Comparing the inversion wind velocity and wind direction with CMCD4 and ECMWF wind vector,the result is good,the run speed is quicker than other method.The good performance of the neural network method suggests that wind retrieval from ERS-1/2 scatterometer is possible. |
| |
| Keywords: | BP-NN scatterometer wind retrieval resolving directional ambiguities |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《海洋学报》浏览原始摘要信息 |
|
点击此处可从《海洋学报》下载全文 |
|
