The European Space Agency's Earth Observation Program

Desnos, Yves-Louis; Borgeaud, M.; Doherty, Mark; Rast, M.; Liebig, Volker

doi:10.1109/mgrs.2014.2319270

Cited by 20 publications

(6 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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.…”

Section: Datamentioning

confidence: 99%

Cloud removal in Sentinel-2 imagery using a deep residual neural network and SAR-optical data fusion

Meraner

Ebel

Zhu

et al. 2020

ISPRS Journal of Photogrammetry and Remote Sensing

254

138

View full text Add to dashboard Cite

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.

show abstract

Section: Datamentioning

confidence: 99%

Cloud removal in Sentinel-2 imagery using a deep residual neural network and SAR-optical data fusion

Meraner

Ebel

Zhu

et al. 2020

ISPRS Journal of Photogrammetry and Remote Sensing

254

138

View full text Add to dashboard Cite

show abstract

“…The data of the Sentinel-2 satellite provided by the European Copernicus Earth Observation Program [1] are free and available globally, and they have been widely used in several agricultural applications, such as crop classification [2], cropland monitoring [3], growth evaluation [4,5], and flood mapping [6]. However, as an optical satellite, Sentinel-2 inevitably suffers from cloud and shadow contamination, which can cause a shortage of efficient Earth surface reflectance data for subsequent research [7,8].…”

Section: Introductionmentioning

confidence: 99%

Deriving Non-Cloud Contaminated Sentinel-2 Images with RGB and Near-Infrared Bands from Sentinel-1 Images Based on a Conditional Generative Adversarial Network

Xiong

Feng

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Sentinel-2 images have been widely used in studying land surface phenomena and processes, but they inevitably suffer from cloud contamination. To solve this critical optical data availability issue, it is ideal to fuse Sentinel-1 and Sentinel-2 images to create fused, cloud-free Sentinel-2-like images for facilitating land surface applications. In this paper, we propose a new data fusion model, the Multi-channels Conditional Generative Adversarial Network (MCcGAN), based on the conditional generative adversarial network, which is able to convert images from Domain A to Domain B. With the model, we were able to generate fused, cloud-free Sentinel-2-like images for a target date by using a pair of reference Sentinel-1/Sentinel-2 images and target-date Sentinel-1 images as inputs. In order to demonstrate the superiority of our method, we also compared it with other state-of-the-art methods using the same data. To make the evaluation more objective and reliable, we calculated the root-mean-square-error (RSME), R2, Kling–Gupta efficiency (KGE), structural similarity index (SSIM), spectral angle mapper (SAM), and peak signal-to-noise ratio (PSNR) of the simulated Sentinel-2 images generated by different methods. The results show that the simulated Sentinel-2 images generated by the MCcGAN have a higher quality and accuracy than those produced via the previous methods.

show abstract

“…Therefore, it is not limited to satellite remote sensing but also includes all in situ and aerial monitoring instruments and networks such as GNSS or seismometer networks, unmanned aerial vehicles or field observations (Antoine et al this issue;Balsamo et al 2018;Salichon et al 2007). We focus here on space-based observations because space agencies have played a prominent role in organizing the community of Earth observations over the last decades (Bally 2012;Desnos et al 2014Desnos et al , 2016. Furthermore, space observations are explicitly recognized as important contributions in the disaster risk reductions strategies of both the Hyogo and Sendai frameworks for the United Nations (2005,2015).…”

Section: Introductionmentioning

confidence: 99%

Space-Based Earth Observations for Disaster Risk Management

et al. 2020

View full text Add to dashboard Cite

As space-based Earth observations are delivering a growing amount and variety of data, the potential of this information to better support disaster risk management is coming into increased scrutiny. Disaster risk management actions are commonly divided into the different steps of the disaster management cycle, which include: prevention, to minimize future losses; preparedness and crisis management, often focused on saving lives; and post-crisis management aiming at re-establishing services supporting human activities. Based on a literature review and examples of studies in the area of coastal, hydro-meteorological and geohazards, this review examines how space-based Earth observations have addressed the needs for information in the area of disaster risk management so far. We show that efforts have essentially focused on hazard assessments or supporting crisis management, whereas a number of needs still remain partly fulfilled for vulnerability and exposure mapping, as well as adaptation planning. A promising way forward to maximize the impact of Earth observations includes multi-risk approaches, which mutualize the collection of time-evolving vulnerability and exposure data across different hazards. Opportunities exist as programmes such as the Copernicus Sentinels are now delivering Earth observations of an unprecedented quality, quantity and repetitiveness, as well as initiatives from the disaster risk science communities such as the development of observatories. We argue that, as a complement to this, more systematic efforts to (1) build capacity and (2) evaluate where space-based Earth observations can support disaster risk management would be useful to maximize its societal benefits.

show abstract

The European Space Agency's Earth Observation Program

Cited by 20 publications

References 2 publications

Cloud removal in Sentinel-2 imagery using a deep residual neural network and SAR-optical data fusion

Cloud removal in Sentinel-2 imagery using a deep residual neural network and SAR-optical data fusion

Deriving Non-Cloud Contaminated Sentinel-2 Images with RGB and Near-Infrared Bands from Sentinel-1 Images Based on a Conditional Generative Adversarial Network

Space-Based Earth Observations for Disaster Risk Management

Contact Info

Product

Resources

About