MétaCan
Menu
Back to cohort
Record W4309235608 · doi:10.1080/2150704x.2022.2136019

Super-resolution of Sentinel-2 images using Wasserstein GAN

2022· article· en· W4309235608 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueRemote Sensing Letters · 2022
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Image Processing Techniques
Canadian institutionsUniversity of Windsor
Fundersnot available
KeywordsMean squared errorImage resolutionResolution (logic)Computer scienceSuperresolutionRemote sensingSatelliteArtificial intelligenceHigh resolutionSpectral bandsPattern recognition (psychology)Generative adversarial networkImage (mathematics)MathematicsGeologyStatisticsPhysics

Abstract

fetched live from OpenAlex

The Sentinel-2 satellites deliver 13 band multi-spectral imagery with bands having 10 m, 20 m or 60 m spatial resolution. The low-resolution bands can be upsampled to match the high resolution bands to extract valuable information at higher spatial resolution. This paper presents a Wasserstein Generative Adversarial Network (WGAN) based approach named as DSen2-WGAN to super-resolve the low-resolution (i.e., 20 m and 60 m) bands of Sentinel-2 images to a spatial resolution of 10 m. A proposed generator is trained in an adversarial manner using the min-max game to super-resolve the low-resolution bands with the guidance of available high-resolution bands in an image. The performance evaluated using metrics such as Signal Reconstruction Error (SRE) and Root Mean Squared Error (RMSE) shows the effectiveness of the proposed approach as compared to the state-of-the-art method, DSen2 as the DSen2-WGAN reduced RMSE by 14.68% and 7%, while SRE improved by almost 4% and 1.6% for 6× and 2× super-resolution. Lastly, for further evaluation, we have used trained DSen2-WGAN model to super-resolve the bands of EuroSAT dataset, a satellite image classification dataset based on Sentinel-2 images. The per band classification accuracy of low-resolution bands shows significant improvement after super-resolution using our proposed approach.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.835
Threshold uncertainty score0.738

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.019
GPT teacher head0.260
Teacher spread0.242 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it