Abstract
Optical remote sensing imagery is at the core of many Earth observation activities. The regular, consistent and global-scale nature of the satellite data is exploited in many applications, such as cropland monitoring, climate change assessment, land-cover and land-use classification, and disaster assessment. However, one main problem severely affects the temporal and spatial availability of surface observations, namely cloud cover. The task of removing clouds from optical images has been subject of studies since decades. The advent of the Big Data era in satellite remote sensing opens new possibilities for tackling the problem using powerful data-driven deep learning methods.In this paper, a deep residual neural network architecture is designed to remove clouds from multispectral Sentinel-2 imagery. SAR-optical data fusion is used to exploit the synergistic properties of the two imaging systems to guide the image reconstruction. Additionally, a novel cloud-adaptive loss is proposed to maximize the retainment of original information. The network is trained and tested on a globally sampled dataset comprising real cloudy and cloud-free images. The proposed setup allows to remove even optically thick clouds by reconstructing an optical representation of the underlying land surface structure.
Highlights
While the data-driven method proposed in this paper is of generic nature and sensor-agnostic, the specific model we train and our experiments focus on satellite imagery provided by the Sentinel satellites of the European Copernicus Earth observation program (Desnos et al, 2014), as these data are globally and freely available in a user-friendly manner
SAR information when reproducing cloud-free regions of the input image. Since such artifacts do not have a correspondence in the original optical image, this leads to a higher reproduction error
It has to be stressed again, that the dataset used for training of the DSen2-CR model is globally sampled, which means that the network needs to learn a highly complex mapping from SAR to optical imagery for virtually every land cover type existing
Summary
While the quality and quantity of satellite observations dramatically increased in recent years, one common problem persists for remote sensing in the optical domain since the first observation until today: cloud cover. As thick clouds appear opaque in all optical frequency bands, the presence thereof completely corrupts the reflectance signal and obstructs the view of the surface underneath. This causes considerable data gaps in both the spatial and temporal domains. An analysis over 12 years of observations by the Moderate Resolution Imaging Spectroradiometer (MODIS) instrument aboard the satellites Terra and Aqua showed that 67% of the Earth’s surface is covered by clouds on average (King et al, 2013). The model is trained on a large dataset containing scenes acquired globally, ensuring its general applicability on any land cover type
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: ISPRS Journal of Photogrammetry and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.