A unified C-band and Ku-band geophysical model function determined by neural network approach

在线阅读 下载PDF 导出详情
摘要 Thegeophysicalmodelfunction(GMF)describestherelationshipbetweenbackscatteringandseasurfacewind,sothatwindvectorscanberetrievedfrombackscatteringmeasurement.TheGMFplaysanimportantroleinoceanwindvectorretrievals,itsperformancewilldirectlyinfluencetheaccuracyoftheretrievedwindvector.Neuralnetwork(NN)approachisusedtodevelopaunifiedGMFforC-bandandKu-band(NN-GMF).EmpiricalGMFCMOD4andQSCAT-1areusedtogeneratethesimulatedtrainingdata-set,andGaussiannoiseatasignalnoiseratioof30dBisaddedtothedata-settosimulatethenoiseinthebackscatteringmeasurement.TheNN-GMFemploysradiofrequencyasanadditionalparameter,soitcanbeappliedforbothC-bandandKu-band.Analysesshowthattheσ0predictedbytheNN-GMFiscomparablewiththeσ0predictedbyCMOD4andQSCAT-1.AlsothewindvectorsretrievedfromtheNN-GMFandempiricalGMFCMOD4andQSCAT-1arecomparable,indicatingthattheNN-GMFisaseffectiveastheempiricalGMF,andhastheadvantagesoftheuniversalform.
机构地区 不详
出处 《海洋学报:英文版》 2008年6期
出版日期 2008年06月16日(中国期刊网平台首次上网日期,不代表论文的发表时间)
  • 相关文献