摘要
A Self-Organizing Feature Mapping (SOM) network model was developed for the retrievals of rain-rate (RR) over oceans from SSM / I measurement, by using the SSM / I and corresponding radar-derived rain-rate data provided by National Space Development Agency of Japan (NASDA). Based on the frequency-distribution of rain-rate samples, the SOM model was constructed in different rain-rate ranges. The model was first trained by five-sixths of the data, and the other data were used to test the retrieval ability of the model. The retrieval results of the SOM model were compared with two statistically-based algorithms. It is shown that the SOM model provides better retrievals of rain-rate.
A Self-Organizing Feature Mapping (SOM) network model was developed for the retrievals of rain-rate (RR) over oceans from SSM / I measurement, by using the SSM / I and corresponding radar-derived rain-rate data provided by National Space Development Agency of Japan (NASDA). Based on the frequency-distribution of rain-rate samples, the SOM model was constructed in different rain-rate ranges. The model was first trained by five-sixths of the data, and the other data were used to test the retrieval ability of the model. The retrieval results of the SOM model were compared with two statistically-based algorithms. It is shown that the SOM model provides better retrievals of rain-rate.
