Sentinel 1
Sentinel-1 is a constellation of radar satellites providing valuable Earth observation data, largely unaffected by cloud cover, crucial for various applications. Current research focuses on integrating Sentinel-1 data with other sources (e.g., Sentinel-2 optical imagery) using advanced machine learning techniques, such as transformer networks and convolutional neural networks, to improve accuracy in tasks like land cover mapping, flood detection, and crop monitoring. This readily available, high-quality data, combined with sophisticated algorithms, significantly enhances the capabilities of remote sensing for diverse scientific and practical applications, including disaster response, precision agriculture, and environmental monitoring.
Papers
Context Compression for Auto-regressive Transformers with Sentinel Tokens
Siyu Ren, Qi Jia, Kenny Q. Zhu
Sentinel: An Aggregation Function to Secure Decentralized Federated Learning
Chao Feng, Alberto Huertas Celdrán, Janosch Baltensperger, Enrique Tomás Martínez Beltrán, Pedro Miguel Sánchez Sánchez, Gérôme Bovet, Burkhard Stiller
Improved flood mapping for efficient policy design by fusion of Sentinel-1, Sentinel-2, and Landsat-9 imagery to identify population and infrastructure exposed to floods
Usman Nazir, Muhammad Ahmad Waseem, Falak Sher Khan, Rabia Saeed, Syed Muhammad Hasan, Momin Uppal, Zubair Khalid
Feature Selection on Sentinel-2 Multi-spectral Imagery for Efficient Tree Cover Estimation
Usman Nazir, Momin Uppal, Muhammad Tahir, Zubair Khalid