Vm. Krasnopolsky et al., A NEURAL-NETWORK AS A NONLINEAR TRANSFER-FUNCTION MODEL FOR RETRIEVING SURFACE WIND SPEEDS FROM THE SPECIAL SENSOR MICROWAVE IMAGER, J GEO RES-O, 100(C6), 1995, pp. 11033-11045
A single, extended-range neural network (SER NN) has been developed to
model the transfer function for special sensor microwave imager (SSM/
I) surface wind speed retrievals. Applied to data sets used in previou
s SSM/I wind speed retrieval studies, this algorithm yields a bias of
0.05 m/s and an rms difference of 1.65 m/s, compared to buoy observati
ons. The accuracy of the SER NN for clear (low moisture) and cloudy (h
igher moisture/light rain) conditions equals the accuracy of NNs train
ed separately for each of these cases. A new moisture retrieval criter
ion based on a single, physically interpretable parameter, cloud liqui
d water, is proposed in conjunction with the SER NN. Using this retrie
val criterion, (1) a moisture retrieval threshold for cloud liquid wat
er of 0.5 kg/m(2) was estimated, and (2) 40% of the data rejected by p
revious rain flags could be recovered. When the SER NN was trained usi
ng this retrieval criterion, a bias of 0.03 mis and an rms value of 1.
58 m/s were obtained and only 2% of the data were rejected. Also, a sl
ight improvement in retrieval accuracy for cloudy conditions was achie
ved (similar to 10%) by including SSM/I brightness temperatures at 85
GHz. Finally, the limitations of NN algorithms are discussed in light
of the present application.