SNSAT: Superresolució aplicada a índex de vegetació a partir d'imatges del satèl·lit

DESCRIPTION:

Currently, satellite-based vegetation monitoring faces limitations in resolution and accuracy, restricting its effectiveness for detailed crop analysis. Traditional satellite imagery, such as that from the Sentinel constellation, provides valuable data but lacks the fine detail needed for precise vegetation and soil assessment. This limitation affects agricultural applications, including viticulture, where high-resolution information is crucial for optimized crop management. 

The project proposes the application of super-resolution techniques on satellite images, specifically with the Sentinel constellation and potentially with better quality images. Using deep learning algorithms, the resolution of these images will be improved to calculate vegetation indices. 

The result is an advanced system that refines satellite imagery, allowing for better decision-making in agriculture. This improvement is expected to be applied in viticulture, offering a more detailed analysis of efficient crop management. Furthermore, these developments could be integrated into studies of efficient water use in more crops, further crops, beyond wine, creating synergies between remote sensing and agronomic needs. We expect to have at the end of the project an application that can be used by agronomists and researchers in this field.