On the Derivation of Volume Decorrelation from TanDEM-X Bistatic Coherence

Abstract

The bistatic interferometric coherence is affected by different sources of error, among which volume decorrelation, which quantifies the amount of noise caused by volume scattering mechanisms. This represents a key quantity not only for the performance assessment of interferometric synthetic aperture radar (SAR) products, but also for a large variety of scientific applications, ranging from land cover classification to physical parameters estimation, such as ice structure, forest height, and biomass retrieval. The magnitude of volume decorrelation can be derived from the total interferometric coherence by properly compensating for all other decorrelation sources. Considering that temporal decorrelation can be neglected for a bistatic system such as TanDEM-X, the remaining decorrelation components can be estimated from the SAR scene characteristics and the system parameters. In the scientific community, it is a common practice to approximate the volume decorrelation with the coherence or to compute it by compensating for the signal-to-noise ratio (SNR) decorrelation only, which typically represents the predominant decorrelation component. The aim of this work is to assess the impact of different decorrelation sources in detail and to provide the readers with a practical procedure for a precise computation of the volume decorrelation from TanDEM-X bistatic data. In particular, we concentrate on the two most relevant decorrelation components: the SNR and the quantization components. Regarding the former, we estimate the noise equivalent sigma naught directly from real SAR data and we provide the users with a set of polynomial coefficients for the retrieval of the system noise floor for each operational TanDEM-X StripMap beam used for the generation of the global digital elevation model. These values are then combined with the backscatter for the retrieval of the scene-based SNR and of the corresponding decorrelation. Concerning the latter, we analyze its dependence on the backscatter local statistics and quantization rate and we provide the reader with a set of empirical lookup tables for quantifying its impact on the coherence. Finally, we provide reasonable assumptions for all other remaining decorrelation sources, discussing two application scenarios in the fields of forest mapping and forest height estimation, which demonstrate the added value of the proposed methodology.