A Deep Learning Solution for Height Inversion on Forested Areas Using Single and Dual Polarimetric TomoSAR

Forest characterization and monitoring are highly important for tracking climate change, using ecology resources, and biodiversity applications. Synthetic aperture radar tomography (TomoSAR) provides the opportunity to reconstruct 3-D structures of the penetrable media relying on multibaseline image acquisition. In forest applications, TomoSAR serves as a powerful technical tool for reconstructing forest height and underlying topography. Presently, a number of reconstruction methods are based on fully polarimetric (FP) TomoSAR (Pol-TomoSAR) datasets which require costly data acquisition. The aim of this letter is to go beyond the limitation of the requirement for full polarization by extending tomographic SAR neural network (TSNN), a neural network for TomoSAR, to the case of single-polarimetric (SP) and dual-polarimetric (DP) TomoSAR data for retrieving forest height and underlying topography. Experimental results indicate that TSNN trained by SP or DP TomoSAR data is a powerful candidate to estimate forest height and underlying topography with high accuracy.