Lessons from applying SRGAN on Sentinel-2 images for LULC classification

• Main Authors: Goh, Yun Si, Chua, Wen Qing, Yean, Seanglidet, Lee, Bu-Sung
• Other Authors: College of Computing and Data Science
• Format: Conference or Workshop Item
• Language: English
• Published: 2024
• Subjects: Computer and Information Science; Classification; Deep learning
• Online Access: https://hdl.handle.net/10356/177692
• Institution: Nanyang Technological University

Satellite images are commonly used to monitor land use land cover (LULC) changes. Unfortunately, publicly available images often lack the resolution required for detailed urban studies. In this study, we enhanced the resolution of Sentinel-2 (S2) satellite images from 10 meters to 2.5 meters using two super-resolution models: Real-SR and Real-ESRGAN. We tested the suitability of the enhanced images for LULC classification of an urban city, Singapore. From our results, colors have mostly been preserved and man-made objects have become sharper. However, the enhanced images also exhibit colour change, darkening, and salt-and-pepper effects. At this stage, there is no conclusive evidence that enhanced images can improve LULC classification. In fact, they have worsened classification accuracy by 17 - 30%, and the Kappa coefficient by 0.2 - 0.4. Although our application of super-resolution on LULC classification is not successful, it is a first attempt and could be further improved.