Neural network emulation of the integral equation model with multiple scattering.

The Integral Equation Model with multiple scattering (IEMM) represents a well-established method that provides a theoretical framework for the scattering of electromagnetic waves from rough surfaces. A critical aspect is the long computational time required to run such a complex model. To deal with this problem, a neural network technique is proposed in this work. In particular, we have adopted neural networks to reproduce the backscattering coefficients predicted by IEMM at L- and C-bands, thus making reference to presently operative satellite radar sensors, i.e., that aboard ERS-2, ASAR on board ENVISAT (C-band), and PALSAR aboard ALOS (L-band). The neural network-based model has been designed for radar observations of both flat and tilted surfaces, in order to make it applicable for hilly terrains too. The assessment of the proposed approach has been carried out by comparing neural network-derived backscattering coefficients with IEMM-derived ones. Different databases with respect to those employed to train the networks have been used for this purpose. The outcomes seem to prove the feasibility of relying on a neural network approach to efficiently and reliably approximate an electromagnetic model of surface scattering.

Bistatic radar configuration for soil moisture retrieval: analysis of the spatial coverage.

Some outcomes of a feasibility analysis of a spaceborne bistatic radar mission for soil moisture retrieval are presented in this paper. The study starts from the orbital design of the configuration suitable for soil moisture estimation identified in a previous study. This configuration is refined according to the results of an analysis of the spatial resolution. The paper focuses on the assessment of the spatial coverage i.e., on the verification that an adequate overlap between the footprints of the antennas is ensured and on the duty cycle, that is the fraction of orbital period during which the bistatic data are acquired. A non-cooperating system is considered, in which the transmitter is the C-band Advanced Synthetic Aperture Radar aboard Envisat. The best performances in terms of duty cycle are achieved if the transmitter operates in Wide Swath Mode. The higher resolution Image Swath Modes that comply with the selected configuration have a duty cycle that is never less than 12% and can exceed 21%. When Envisat operates in Wide Swath Mode, the bistatic system covers a wide latitude range across the equator, while in some of the Image Swath Modes, the bistatic measurements, collected from the same orbit, cover mid-latitude areas. In the latter case, it might be possible to achieve full coverage in an Envisat orbit repeat cycle, while, for a very large latitude range such as that covered in Wide Swath Mode, bistatic acquisitions could be obtained over about 65% of the area.

Coupling a Neural Network-Based forward Model and a Bayesian Inversion Approach to Retrieve Wind Field from Spaceborne Polarimetric Radiometers.

A simulation study to assess the potentiality of sea surface wind vector estimation based on the approximation of the forward model through Neural Networks and on the Bayesian theory of parameter estimation is presented. A polarimetric microwave radiometer has been considered and its observations have been simulated by means of the two scale model. To perform the simulations, the atmospheric and surface parameters have been derived from ECMWF analysis fields. To retrieve wind speed, Minimum Variance (MV) and Maximum Posterior Probability (MAP) criteria have been used while, for wind direction, a Maximum Likelihood (ML) criterion has been exploited. To minimize the cost function of MAP and ML, conventional Gradient Descent method, as well as Simulated Annealing optimization technique, have been employed. Results have shown that the standard deviation of the wind speed retrieval error is approximately 1.1 m/s for the best estimator. As for the wind direction, the standard deviation of the estimation error is less than 13° for wind speeds larger than 6 m/s. For lower wind velocities, the wind direction signal is too weak to ensure reliable retrievals. A method to deal with the non-uniqueness of the wind direction solution has been also developed. A test on a case study has yielded encouraging results.

Inversion of Electromagnetic Models for Bare Soil Parameter Estimation from Multifrequency Polarimetric SAR Data.

The potentiality of polarimetric SAR data for the estimation of bare soil geophysical parameters (i.e., roughness and soil moisture) is investigated in this work. For this purpose, two forward models available in the literature, able to simulate the measurements of a multifrequency radar polarimeter, have been implemented for use within an inversion scheme. A multiplicative noise has been considered in the multidimensional space of the elements of the polarimetric Covariance Matrix, by adopting a complex Wishart distribution to account for speckle effects. An additive error has been also introduced on the simulated measurements to account for calibration and model errors. Maximum a Posteriori Probability and Minimum Variance criteria have been considered to perform the inversion. As for the algorithms to implement the criteria, simple optimization/integration procedures have been used. A Neural Network approach has been adopted as well. A correlation between the roughness parameters has been also supposed in the simulation as a priori information, to evaluate its effect on the estimation accuracy. The methods have been tested on simulated data to compare their performances as function of number of looks, incidence angles and frequency bands, thus identifying the best radar configuration in terms of estimation accuracy. Polarimetric measurements acquired during MAC Europe and SIR-C campaigns, over selected bare soil fields, have been also used as validation data.

Topographic Effects on the Surface Emissivity of a Mountainous Area Observed by a Spaceborne Microwave Radiometer.

A simulation study to understand the influence of topography on the surfaceemissivity observed by a satellite microwave radiometer is carried out. We analyze theeffects due to changes in observation angle, including the rotation of the polarization plane.A mountainous area in the Alps (Northern Italy) is considered and the information on therelief extracted from a digital elevation model is exploited. The numerical simulation refersto a radiometric image, acquired by a conically-scanning radiometer similar to AMSR-E,i.e., flying at 705 km of altitude with an observation angle of 55°. To single out the impacton surface emissivity, scattering of the radiation due to the atmosphere or neighboringelevated surfaces is not considered. C and X bands, for which atmospheric effects arenegligible, and Ka band are analyzed. The results indicate that the changes in the localobservation angle tend to lower the apparent emissivity of a radiometric pixel with respectto the corresponding flat surface characteristics. The effect of the rotation of thepolarization plane enlarges (vertical polarization), or attenuates (horizontal polarization)this decrease. By doing some simplifying assumptions for the radiometer antenna, theconclusion is that the microwave emissivity at vertical polarization is underestimated,whilst the opposite occurs for horizontal polarization, except for Ka band, for which bothunder- and overprediction may occur. A quantification of the differences with respect to aflat soil and an approximate evaluation of their impact on soil moisture retrieval areyielded.

Integrating Physical and Topographic Information Into a Fuzzy Scheme to Map Flooded Area by SAR.

A flood mapping procedure based on a fuzzy sets theory has been developed. The method is based on the integration of Synthetic Aperture Radar (SAR) measurements with additional data on the inundated area, such as a land cover map and a digital elevation model (DEM). The information on land cover has allowed us to account for both specular reflection, typical of open water, and double bounce backscattering, typical of forested and urban areas. DEM has been exploited to include simple hydraulic considerations on the dependence of inundation probability on surface characteristics. Contextual information has been taken into account too. The proposed algorithm has been tested on a flood occurred in Italy on November 1994. A pair of ERS-1 images, collected before and after (three days later) the flood, has been used. The results have been compared with the data provided by a ground survey carried out when the flood reached its maximum extension. Despite the temporal mismatch between the survey and the post-inundation SAR image, the comparison has yielded encouraging results, with the 87% of the pixels correctly classified as inundated.