Arctic Wintertime Sea Ice Lead Detection from Sentinel-1 SAR Images
Bibliographic record
Abstract
Leads in sea ice cover are almost linear fractures within the pack ice, and are commonly observed in the polar regions. In winter, leads promote energy flux from the underlying ocean to the atmosphere. Synthetic aperture radar (SAR) can monitor leads with a fine spatial resolution, regardless of solar illumination and atmospheric conditions. In this paper, we present an approach for automatic sea ice lead detection (SILDET) in the Arctic wintertime using Sentinel-1 SAR images. SILDET is made up of four modules: 1) a segmentation module; 2) a balance module; 3) an optimization module; and 4) a mask module. The validation results presented in this paper show that SILDET has the capability of detecting open and frozen leads at different stages of freezing. The lead map obtained from SILDET was compared to a lead dataset based on Moderate Resolution Imaging Spectroradiometer (MODIS) data and validated by the use of Sentinel-2 images. This shows that SILDET can provide a more detailed distribution of leads and better estimation of lead width and area. Compared with visual interpretation of Sentinel-1 images, the overall detection accuracy is 97.80% and the Kappa coefficient is 0.88 (for all types). The pyramid scene parsing network (PSPNet) in the segmentation module shows a better performance in detecting frozen leads, compared with the deep learning methods of UNet and DeepLabv3+. The optimization module utilizing shape features also improves the precision in detecting frozen leads. SILDET was applied to present the Arctic lead distribution in January and April 2023 with a spatial resolution of 40 m. The Arctic-wide lead width distribution follows a power law with an exponent of 1.64 ± 0.07. SILDET can be expected to provide long-term high-resolution lead distribution records.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".