Generating Synthetic Multispectral Satellite Imagery from Sentinel-2
This work addresses the problem of data scarcity for building supervised machine learning models using multi-spectral satellite imagery, which is a challenge for environmental and socio-economic applications.
This paper proposes a generative model to produce multi-resolution multi-spectral imagery from Sentinel-2 data. The synthetic images generated by the model are indistinguishable from real images by human observers.
Multi-spectral satellite imagery provides valuable data at global scale for many environmental and socio-economic applications. Building supervised machine learning models based on these imagery, however, may require ground reference labels which are not available at global scale. Here, we propose a generative model to produce multi-resolution multi-spectral imagery based on Sentinel-2 data. The resulting synthetic images are indistinguishable from real ones by humans. This technique paves the road for future work to generate labeled synthetic imagery that can be used for data augmentation in data scarce regions and applications.