Towards automated lake ice classification using dual polarization RADARSAT SAR imagery
Bibliographic record
Abstract
Lake ice, as one of the most important component of the cryosphere, is a valuable indicator of climate change and variability. The Laurentian Great Lakes are the world’s largest supply of freshwater and their ice cover has a major impact on regional weather and climate, ship navigation, and public safety. Monitoring detailed ice conditions on large lakes requires the use of satellite-borne synthetic aperture radar (SAR) data that provide all-weather sensing capabilities, high resolution, and large spatial coverage. Ice experts at the Canadian Ice Service (CIS) have been manually producing operational Great Lakes image analysis charts based on visual interpretation of the SAR images. Ice services such as the CIS would greatly benefit from the availability of an automated or semi-automated SAR ice classification algorithm. We investigated the performance of the unsupervised segmentation algorithm “glocal” iterative region growing with semantics (IRGS) for lake ice classification using dual polarized RADARSAT-2 imagery. Here, the segmented classes with arbitrary labels are manually labelled based on visual interpretation. IRGS was tested on 26 RADARSAT-2 scenes acquired over Lake Erie during winter 2014, and the results were validated against the manually produced CIS image analysis charts. Analysis of various case studies indicated that the “glocal” IRGS algorithm can provide a reliable ice-water classification using dual polarized images with a high overall accuracy of 90.2%. The improvement of using dual-pol as opposed to single-pol images for ice-water discrimination was also demonstrated. For lake ice type classification, most thin ice types were effectively identified but thick and very thick lake ice were often confused due to the ambiguous relation between backscatter and ice types. Texture features could be included for further improvement. Overall, our “glocal” IRGS classification results are close to visual interpretation by ice analysts and would have expected to be closer if they could draw ice charts at a more detailed level.
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 | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".