The Passive Microwave Neural Network Precipitation Retrieval (PNPR) for the Cross-track Scanning ATMS Radiometer

Within the H-SAF program (Satellite Application Facility on Support to Operational Hydrology and Water Management, http://hsaf.meteoam.it) we have developed a new Passive microwave Neural network Precipitation Retrieval algorithm (PNPR v2) designed to work with the passive microwave Advanced Technology Microwave Sounder (ATMS) cross-track scanning radiometer (on board the Suomi-NPP satellite). The algorithm, based on the artificial neural network approach, is an evolution of the original PNPR algorithm developed for the Advanced Microwave Sounding Unit/Microwave Humidity Sounder (AMSU-A/MHS) radiometers (on board the European MetOp and U.S. NOAA satellites) and used operationally within the H-SAF program. The main algorithm improvements are the design and development of a new neural network able to manage the information derived from the additional ATMS channels (respect to the AMSU-A/MHS radiometer). Both, PNPR and PNPR v2, are optimized for the European and the African area, and use a unique neural network that retrieves the surface precipitation rate for all types of surface backgrounds represented in its training database, i.e., land (vegetated or arid), ocean, snow/ice or coast. The preliminary results obtained in a verification study over Europe and Africa, using for comparison the available ground-based radar data and the spaceborne GPM Ku and Ku+Ka radar observations, are presented in this paper