Mapping Slums in Mumbai, India, Using Sentinel-2 Imagery: Evaluating Composite Slum Spectral Indices (CSSIs)

Accurate geographic data of slums are important for handling urban poverty issues. Previous slum mapping studies using high-resolution or very-high-resolution (HR/VHR) remotely sensed (RS) images are commonly not suitable for city-wide scale tasks. This study aims to efficiently generate a slum map on a city-wide scale using freely accessed multispectral medium-resolution (MR) Sentinel-2 images. Composite slum spectral indices (CSSIs) were initially proposed based on the shapes of spectral profiles of slums and nonslums and directly represent slum characteristics. Specifically, CSSI-1 denotes the normalized difference between the shortwave infrared bands and the red edge band, while CSSI-2 denotes the normalized difference between the blue band and the green band. Furthermore, two methods were developed to test the effectiveness of CSSIs on slum mapping, i.e., the threshold-based method and the machine learning (ML)-based method. Experimental results show that the threshold-based method and the ML-based method achieve intersection over unions (IoU) of 43.89% and 54.45% in Mumbai, respectively. The accuracies of our methods are comparable to or even higher than the accuracies reported by existing methods using HR/VHR images and transfer learning. The threshold-based method exhibits a promising performance in mapping slums larger than 5 ha, while the ML-based method refines mapping accuracies for slum pockets smaller than 5 ha. The threshold-based method and the ML-based method produced the slum map in Mumbai in 2 and 28 min, respectively. Our methods are suitable for rapid large-area slum mapping owing to the high data availability of Sentinel-2 images and high computational efficiency.

Automated summary

This study proposes two methods based on composite slum spectral indices (CSSIs) to efficiently generate slum maps on a city-wide scale using medium-resolution Sentinel-2 images. The results show that the accuracies of these methods are comparable to or even higher than existing methods using high-resolution images and transfer learning. The threshold-based method performs well for larger slum areas, while the machine learning-based method improves accuracy for smaller slum pockets.