Built-up area mapping using Sentinel-1 SAR data

Abstract

A timely and accurate spatial mapping of built-up areas (BA) is crucial in making cities and human settlements safe, resilient, and sustainable. Synthetic Aperture Radar (SAR) data are useful for BA mapping due to strong coherent backscatter from diverse human-made targets, distinct texture patterns, and sensitivity to its geometric characteristics. However, BA mapping using SAR data is still challenging due to various geometrical and physical factors that often lead to misinterpretations. Therefore, this study presents a novel method to map BA using single-date dual polarized Sentinel-1 SAR data to overcome such challenges in complex built-up scenarios. Here, we propose three normalized descriptors derived from the Stokes vector elements. These three descriptors are found to be vital in characterizing different types of BA structures. We then consider the symmetric quadratic mean of the normalized descriptors to propose a novel dual polarimetric radar built-up index (DpRBI). The proposed index provides information about the average normalized polarized power, which is useful for mapping diverse types of BA or their combination in an image. We assess the proposed methodology utilizing the Sentinel-1 image acquired over three major cities: Delhi, Milan, and Barcelona. The BA map accuracy for all three cities was found to be ≈ 85% with a low BA omission error. We compared the mapping results with available BA/land cover products: World Settlement Footprint 2019 (WSF-19) and World cover 2020 (WC-20). The BA map obtained using the proposed index was better than WSF-19 and WC-20, particularly for BA omission errors. For example, we observed a relatively low BA omission error of 22.34% using DpRBI compared to 31.86% and 41.79% for WC-20 and WSF-19, respectively, over Milan, Italy. The code is available at: https://github.com/navv37/DpRBI