VENμS: Mission Characteristics, Final Evaluation of the First Phase and Data Production

Dick, A.; Raynaud, Jean-Louis; Rolland, A.; Pelou, Sophie; Coustance, S.; Dedieu, Gérard; Hagolle, Olivier; Burochin, Jean-Pascal; Binet, Renaud; Moreau, Agathe

doi:10.3390/rs14143281

Cited by 8 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of course, this is prior to the new GRI processing that was set up in April 2021, but since the reprocessing is still ongoing, most products in the Theia archive will have this accuracy, which corresponds to two pixels from VENµS. On the VENµS side, partly because of the narrower field of view, accuracy is measured to be 3 m for 93% of the images [32]. Since the aim of the SEN2VENµS dataset is to serve for the training of super-resolution algorithms, correct alignments of images is of great importance.…”

Section: Spatial Registrationmentioning

confidence: 99%

SEN2VENµS, a Dataset for the Training of Sentinel-2 Super-Resolution Algorithms

Michel

Vinasco-Salinas

Inglada

et al. 2022

Data

Self Cite

View full text Add to dashboard Cite

Boosted by the progress in deep learning, Single Image Super-Resolution (SISR) has gained a lot of interest in the remote sensing community, who sees it as an opportunity to compensate for satellites’ ever-limited spatial resolution with respect to end users’ needs. This is especially true for Sentinel-2 because of its unique combination of resolution, revisit time, global coverage and free and open data policy. While there has been a great amount of work on network architectures in recent years, deep-learning-based SISR in remote sensing is still limited by the availability of the large training sets it requires. The lack of publicly available large datasets with the required variability in terms of landscapes and seasons pushes researchers to simulate their own datasets by means of downsampling. This may impair the applicability of the trained model on real-world data at the target input resolution. This paper presents SEN2VENµS, an open-data licensed dataset composed of 10 m and 20 m cloud-free surface reflectance patches from Sentinel-2, with their reference spatially registered surface reflectance patches at 5 m resolution acquired on the same day by the VENµS satellite. This dataset covers 29 locations on earth with a total of 132,955 patches of 256 × 256 pixels at 5 m resolution and can be used for the training and comparison of super-resolution algorithms to bring the spatial resolution of 8 of the Sentinel-2 bands up to 5 m.

show abstract

Section: Spatial Registrationmentioning

confidence: 99%

SEN2VENµS, a Dataset for the Training of Sentinel-2 Super-Resolution Algorithms

Michel

Vinasco-Salinas

Inglada

et al. 2022

Data

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition, combining different mapping approaches from several RS platforms [17], using new LiDAR technics detection in changes soil surface [20] or drone-based RS [25] are opportunities in the mapping of WE for future studies. The new very-high resolution satellite systems such as Venus (Israel Space Agency and National Center for Space Studies, France) [191], Gaofen (China) [192], or Planet Satellites [193] bring more detailed images. The spatial and temporal resolution will also increase for upcoming hyperspectral missions such as Copernicus Chime (ESA) [194], HysIS (Indian Space Research Organisation), EnMAP (Environmental Monitoring and Analysis Program) [195], radar mission Copernicus Rose-L [196] and CIMR (ESA) [197], SCATSAT-1 [198], and NovaSAR-01 (CSIRO Centre for Earth Observation) [199].…”

Section: Future Directionsmentioning

confidence: 99%

Unlocking the Potential of Remote Sensing in Wind Erosion Studies: A Review and Outlook for Future Directions

et al. 2023

View full text Add to dashboard Cite

Remote sensing (RS) has revolutionized field data collection processes and provided timely and spatially consistent acquisition of data on the terrestrial landscape properties. This research paper investigates the relationship between Wind Erosion (WE) and Remote Sensing (RS) techniques. By examining, analyzing, and reviewing recent studies utilizing RS, we underscore the importance of wind erosion research by exploring indicators that influence the detection, evaluation, and modeling of wind erosion. Furthermore, it identifies research gaps particularly in soil erodibility estimation, soil moisture monitoring, and surface roughness assessment using RS. Overall, this research enhances our understanding of WE and RS and offers insights into future research directions. To conduct this study, we employed a two-fold approach. First, we utilized a non-systematic review approach by accessing the Global Applications of Soil Erosion Modelling Tracker (GASEMT) database. Subsequently, we conducted a systematic review of the relevant literature on wind erosion and remote sensing in the core collection of the Web of Science (WoS) database. Additionally, we employed the VOSviewer bibliometric software to generate a cooperative keyword network analysis, facilitating the advancements and identifying emerging areas of WE and RS research. With a non-systematic review, we focused on examining the current state and potential of remote sensing for mapping and analyzing following indicators of wind erosion modelling: (1) soil erodibility; (2) soil moisture; (3) surface roughness; (4) vegetation cover; (5) wind barriers; and (6) wind erosion mapping. Our study highlights the widespread utilization of freely available RS data, such as MODIS and Landsat, for WE modeling. However, we also acknowledge the limitations of high resolution sensors due to their high costs. RS techniques offer an efficient and cost-effective approach for mapping erosion at various scales and call for a more comprehensive and detailed assessment of soil erosion at regional scales. These findings provide valuable guidance for future research endeavors in this domain.

show abstract

“…Of course this is prior to the new GRI processing that has been set-up in April 2021, but since the reprocessing is still undergoing, most products in Theia archive will have this accuracy, which corresponds to 2 pixels from VENµS. On VENµS side, partly because of the narrower field of view, accuracy is measured to be 3 meters for 93% of the images [17]. Since the aim of the SEN2VENµS dataset is to serve for the training of super-resolution algorithms, correct alignments of images is of great importance.…”

Section: Spatial Registrationmentioning

confidence: 99%

SEN2VENµS, a Dataset for the Training of Sentinel-2 Super-Resolution Algorithms

Michel¹,

Vinasco-Salinas²,

Inglada³

et al. 2022

Preprint

View full text Add to dashboard Cite

Boosted by the progress in deep learning, Single Image Super-Resolution (SISR) has gained a lot of interest in the Remote Sensing community, who sees it as an oportunity to compensate for satellite's ever-limited spatial resolution with respect to end users needs. While there has been a great amount of work on network architures in the latest years, deep learning based SISR in remote sensing is still limited by the availability of the large training sets it requires. The lack of publicly available large datasets with the required variability in terms of landscapes and seasons pushes researchers to simulate their own dataset by means of downsampling. This may impair the applicability of the trained model on real world data at the target input resolution. In this paper, we propose an open-data licenced dataset composed of 10m and 20m cloud-free surface reflectance patches from Sentinel-2, with their reference spatially-registered surface reflectance patches at 5 meter resolution acquired on the same day by the VENµS satellite. This dataset covers 29 locations on earth with a total of 132 955 patches of 256x256 pixels at 5 meters resolution, and can be used for the training of super-resolution algorithms to bring the spatial resolution of 8 of the Sentinel-2 bands down to 5 meters.

show abstract

VENμS: Mission Characteristics, Final Evaluation of the First Phase and Data Production

Cited by 8 publications

References 27 publications

SEN2VENµS, a Dataset for the Training of Sentinel-2 Super-Resolution Algorithms

SEN2VENµS, a Dataset for the Training of Sentinel-2 Super-Resolution Algorithms

Unlocking the Potential of Remote Sensing in Wind Erosion Studies: A Review and Outlook for Future Directions

SEN2VENµS, a Dataset for the Training of Sentinel-2 Super-Resolution Algorithms

Contact Info

Product

Resources

About