论文部分内容阅读
A neural network methodology is presented to retrieve wind vectors from ERS-1/2 scatterometer data. The wind directional ambiguities are eliminated by a circular median filter algorithm. All data come from ERS-1/2 scatterometer data collocated pairs with CMCD4 vector. Comparing the results with CMCD4 and ECMWF wind vector,they agree well, which indicates that it is possible to extract wind vector from the ERS1/2 scatterometer with the neural network method.
A neural network methodology is presented to retrieve wind vectors from ERS-1/2 scatterometer data. The wind directional ambiguities were eliminated by a circular median filter algorithm. All data come from ERS-1/2 scatterometer data collocated pairs with CMCD4 vector. the results with CMCD4 and ECMWF wind vector, they agree well, which indicates that it is possible to extract wind vector from the ERS1 / 2 scatterometer with the neural network method.