In this work a method based on neural networks is proposed to retrieve precipitable water vapour over land and over ocean from brightness temperatures measured by the Advanced Microwave Scanning Radiometer - Earth Observing System. In order to train the neural network, water vapour values provided by European Centre for Medium-Range Weather Forecasts, sampled on a regular grid with a spacing of 0.25deg in latitude and longitude, were exploited. The analysis was performed over Italy and the Mediterranean area and, as expected, the water vapour retrieval over a sea background exhibits good accuracy. Over a land background the proposed approach seems to be promising, where a RMS error of about 0.3 cm was achieved.
Development of a neural network for precipitable water vapour retrieval over ocean and land
BASILI, Patrizia;BONAFONI, Stefania;
2008
Abstract
In this work a method based on neural networks is proposed to retrieve precipitable water vapour over land and over ocean from brightness temperatures measured by the Advanced Microwave Scanning Radiometer - Earth Observing System. In order to train the neural network, water vapour values provided by European Centre for Medium-Range Weather Forecasts, sampled on a regular grid with a spacing of 0.25deg in latitude and longitude, were exploited. The analysis was performed over Italy and the Mediterranean area and, as expected, the water vapour retrieval over a sea background exhibits good accuracy. Over a land background the proposed approach seems to be promising, where a RMS error of about 0.3 cm was achieved.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
