Estimation of physical parameters of crops by polarimetric SAR interferometry with TanDEM-X sensor data

Abstract

Polarimetric SAR Interferometry (PolInSAR) is a radar remote sensing technique sensitive to different structural variables of scenes with vegetation, such as the height of the plants, the biomass and internal profile, the underlying topography, etc. Historically, it has been used in forests, specially with data measured with airborne sensors, and also, since 2012, with data from the TanDEM-X satellite sensor, formed by two X-band radar satellites with very close orbits. In contrast, the application of PolInSAR to agriculture had not been possible with satellite data due to baseline requirements (separation between satellite positions), since it must be, at least, 10 times greater than in the case of forests. From April to September 2015 a special campaign was carried out with TanDEM-X during which the satellites were separated at the required distance. The first results obtained when applying these data to the height measurement of rice plants in areas of the provinces of Seville and Valencia, as well as in Turkey, have been recently published. However, there are still many questions to be solved, as well as aspects to improve, to fully validate this technique with satellite data. For instance, the influence of the bistatic configuration on the observations and on the estimations of the variables of the scene must be quantified. Moreover, the estimation of other variables other than height has not been tested yet. Finally, this technique should be tested on other types of crops. This master’s degree project explores the aforementioned aspects, for which the algorithms of data processing and parameter estimation are implemented, and the different options are evaluated through their validation against field data and from the computational point of view. The main contribution of this work is the evaluation for the first time of the PolIn-SAR technique applied to crops with satellite data, as well as the generation of open source (python) for its distribution in repositories.