Snow Cover Mapping With Poincare Sphere Parameters From Polsar Images Using An Auto-Encoder Network

This paper presents a novel framework for snow cover mapping with multi-basis Poincare sphere parameters obtained from full-polarimetric SAR images in conjunction with an Auto-Encoder neural network. The neural network comprises of two stages where an unsupervised stochastic sampling Auto-Encoder (AE) learns a summarized representation of multi-basis polarimetric SAR data, and a supervised Feed Forward (If) network performs classification. The proposed algorithm is demonstrated for snow-cover mapping using the Radarsat-2 (FQ-28) C-band full-polarimetric SAR datasets acquired over the Manali-Dhundi region of-Himachal Pradesh, India, The results are visualized along with the NDSI-based snow cover map derived from the LANDSAT-8 imagery for the region.