Super-resolution of Sentinel-2 images using Wasserstein GAN
Bibliographic record
Abstract
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".