A Neural Network Based Single Footprint Temperature Retrieval for Atmospheric Infrared Sounder Measurements and Its Application to Study on Stratospheric Gravity Wave

Satellite hyperspectral infrared sounder measurements have better horizontal resolution than other sounding techniques as it boasts the stratospheric gravity wave (GW) analysis. To accurately and efficiently derive the three- dimensional structure of the stratospheric GWs from the single-field-of-view (SFOV) Atmospheric InfraRed Sounder (AIRS) observations, this paper firstly focuses on the retrieval of the atmospheric temperature profiles in the altitude range of 20-60 km with an artificial neural network approach (ANN). The simulation experiments show that the retrieval bias is less than 0.5 K, and the root mean square error (RMSE) ranges from 1.8 to 4 K. Moreover, the retrieval results from 20 granules of the AIRS observations with the trained neural network (AIRS_SFOV) and the corresponding operational AIRS products (AIRS_L2) as well as the dual-regression results from the Cooperative Institute for Meteorological Satellite Studies (CIMSS) (AIRS_DR) are compared respectively with ECMWF T799 data. The comparison indicates that the standard deviation of the ANN retrieval errors is significantly less than that of the AIRS_DR. Furthermore, the analysis of the typical GW events induced by the mountain Andes and the typhoon "Soulik" using different data indicates that the AIRS_SFOV results capture more details of the stratospheric gravity waves in the perturbation amplitude and pattern than the operational AIRS products do.