A new neural network approach including first guess for retrieval of atmospheric water vapor, cloud liquid water path, surface temperature, and emissivities over land from satellite microwave observations

Abstract

The analysis of microwave observations over land to determine atmospheric and surface parameters is still limited due to the complexity of the inverse problem. Neural network techniques have already proved successful as the basis of efficient retrieval methods for nonlinear cases; however, first guess estimates, which are used in variational assimilation methods to avoid problems of solution nonuniqueness or other forms of solution irregularity, have up to now not been used with neural network methods. In this study, a neural network approach is developed that uses a first guess. Conceptual bridges are established between the neural network and variational assimilation methods. The new neural method retrieves the surface skin temperature, the integrated water vapor content, the cloud liquid water path and the microwave surface emissivities between 19 and 85 GHz over land from Special Sensor Microwave Imager observations. The retrieval, in parallel, of all these quantities improves the results for consistancy reasons. A database to train the neural network is calculated with a radiative transfer model and a global collection of coincident surface and atmospheric parameters extracted from the National Center for Environmental Prediction reanalysis, from the International Satellite Cloud Climatology Project data, and from microwave emissivity atlases previously calculated. The results of the neural network inversion are very encouraging. The theoretical RMS error of the surface temperature retrieval over the globe is 1.3 K in clear‐sky conditions and 1.6 K in cloudy scenes. Water vapor is retrieved with a theoretical RMS error of 3.8 kg m−2 in clear conditions and 4.9 kg m−2 in cloudy situations. The theoretical RMS error in cloud liquid water path is 0.08 kg m−2. The surface emissivities are retrieved with an accuracy of better than 0.008 in clear conditions and 0.010 in cloudy conditions. Microwave land surface temperature retrieval presents a very attractive complement to the infrared estimates in cloudy areas: time record of land surface temperature will be produced.