Utilizing Sentinel 1 and 2 data for researching high-density urban areas

Authors: Shrobona Karkun-Sen*, Temple University, Víctor Hugo Gutiérrez Vélez, Temple university
Topics: Land Use and Land Cover Change, Remote Sensing, Asia
Keywords: urban remote sensing, Indian cities, urban spatial research, machine learning, supervised classification, urban transportation, remote sensing, land cover classification
Session Type: Virtual Paper
Day: 4/10/2021
Start / End Time: 1:30 PM / 2:45 PM
Room: Virtual 22
Presentation File: No File Uploaded


India’s metropolitan regions have expanded to colossal proportions in the past two decades, with over 30% of its population living in urban areas. Thus, understanding patterns of land use in the context of rapid urban transformation is becoming increasingly vital to address urban sustainability. The availability of new, high quality, medium resolution satellite products such as Sentinel along with advancements in research methods is enabling researchers to inquire about the current state of land use in urban areas and offer new opportunities for mapping urban landscapes. However, supervised classification studies using Sentinel products are relatively new. Here, we utilize linear spectral unmixing and data fusion techniques with a machine-learning algorithm to classify densely built, heterogeneous urban areas in Delhi’s metropolitan region. We also analyze the classification results in proximity to transportation systems to test their relationship with urban density. Data from both Sentinel-I (active radar sources) and Sentinel-II (optical reflectance), as well as the locations of Metro Rail infrastructure, will be used to complete the analysis. The findings demonstrate that the fusion of optical and SAR data from Sentinel satellites (at XX%) has better accuracy than classification models that utilize data from only one source (at XX% for Sentinel 1 and XX% for Sentinel 2).
Finally, this study demonstrates that there is a wide variety of land uses with built density in the study area, which needs to be further understood in the context of their proximity to transportation networks and changing urban infrastructure.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login