Investigating and Analyzing the Performance of Spectral Indices in Urban Extraction by Multi-spectral Satellite Images

Population growth has resulted in rapid changes in urban landscapes in many countries, including Iran. Monitoring urban areas can be accelerated by utilizing remote sensing images and spectral indices in urban planning. This requires evaluating the performance of indices according to the application in different conditions, which can be challenging for users. This study was conducted to compare and analyze suitable solutions for analyzing urban indicators using satellite imagery and their effectiveness. For this purpose, Landsat-8 and Sentinel-2 images were first analyzed to extract spectral index; then automated threshold algorithms were applied to separate constructed areas. Results indicate that Sentinel-2 images perform better than Landsat images in general. Among the spectral indices, the UI index for Landsat and Sentinel-2 images in Rafsanjan with overall accuracy of 86.28 and 98.19, the NBI index for Landsat and Sentinel-2 images in Amol city with overall accuracy of 87.21 and 97.48, and the UI index in Landsat and IBI in Sentinel-2 for Isfahan with overall accuracy of 78.73 and 91.69 have the best performance. Furthermore, applying the manual threshold limit to weak indicators has increased accuracy in most cases. Another study used Sentinel-1 images with user-controlled thresholds to identify built-up areas, and the results for Amol, Rafsanjan, and Isfahan were 89.24, 80.03, and 76.10, respectively. The findings of this study revealed that the performance accuracy of indices can vary depending on parameters such as the type of climate, different sensors, and thresholds. Therefore, as a strategic model, the results of this analysis can provide researchers with a better understanding of indicators as a result of considering different parameters.