A multilayer neural network has been developed to retrieve IPWV over land from brightness temperatures measured by the Advanced Microwave Scanning Radiometer - Earth Observing System (AMSR-E) on board the Aqua satellite. Our study was optimized over two areas in Northern and Central Italy. Good agreements on the order of 0.24 cm and 0.33 cm rms, respectively, were found between neural network retrievals and ECMWF IPWV data for clear-sky. In the presence of clouds, an rms of the order of 0.38 cm was found for both areas. © 2010 IEEE.
Neural network for the satellite retrieval of precipitable water vapor over land / Vinia, Mattioli; Stefania, Bonafoni; Patrizia, Basili; G., Carlesimo; Piero, Ciotti; Pulvirenti, Luca; Pierdicca, Nazzareno. - (2010), pp. 2960-2963. (Intervento presentato al convegno 2010 30th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010 tenutosi a Honolulu, HI nel 25 July 2010 through 30 July 2010) [10.1109/igarss.2010.5650528].
Neural network for the satellite retrieval of precipitable water vapor over land
PULVIRENTI, Luca;PIERDICCA, Nazzareno
2010
Abstract
A multilayer neural network has been developed to retrieve IPWV over land from brightness temperatures measured by the Advanced Microwave Scanning Radiometer - Earth Observing System (AMSR-E) on board the Aqua satellite. Our study was optimized over two areas in Northern and Central Italy. Good agreements on the order of 0.24 cm and 0.33 cm rms, respectively, were found between neural network retrievals and ECMWF IPWV data for clear-sky. In the presence of clouds, an rms of the order of 0.38 cm was found for both areas. © 2010 IEEE.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
