A neural network multiparameter algorithm for SSM/I ocean retrievals: Comparisons and validations

A new empirical multiparame Special Sensor Microwave/Imager (SSM/I) retrieval algorithm based on the neural network approach, which retrieves wind speed, columnar renter vapor and columnar liquid water simultaneously using only SSM/I brightness temperatures, is compared with existing global SSM/I refrieoal algorithms. In terms of wind speed retrieval accuracy, the were algorithm systematically outperforms all algorithms considered under all weather conditions where retrievals are possible with an algorithm rms error of 1.0 m/s under clear and 1.3 m/s tinder clear plus cloudy conditions. It also generates high wind speeds with acceptable accuracy. This improvement in accuracy is coupled with increased areal coverage rc;ith obvious benefits for operational applications. With respect to columnar water vapor and columnar liquid water, the new algorithm reproduces the results of existing algorithms closely. The new algorithm has been tested and accepted for operational use at the National Centers for Environmental Prediction (NCEP) producing a positive impact on forecast winds through assimilation into NCEP's numerical weather prediction models. (C) Elsevier Science Inc., 2000.