PIXEL-BASED SEA ICE CLASSIFICATION USING THE MAGSIC SYSTEM
Bibliographic record
Abstract
MAGSIC is an operation-oriented system in development dedicated to map-guided classification of sea ice for navigation route planning and meteorological modelling. It has already produced promising results in difficult situations such as the Gulf of Saint-Lawrence in late winter. The Canadian Ice Service (CIS) produces ice maps made of large regions with relatively homogeneous concentrations of different ice types. MAGSIC uses the information of these maps to produce a pixel-based (rather than region-based) ice map by labelling a Markov random field (MRF) segmentation of RADARSAT-1 data along with its derived texture features. The system uses a novel implementation of MRF segmentation in combination with a unique labelling approach based on “cognitive reasoning”. Although reasonably successful, the system often had difficulties identifying ice type that required cues based on the shape recognition of large ice floes or leads. This article aims at thoroughly testing the MAGSIC system using validation data acquired during the “2003 Gulf of Saint-Lawrence SAR Validation Field Program ” performed by CIS. Some new features were also added to MAGSIC and were evaluated. Results suggest a reasonable success and that the errors can be partially attributed to the generalized nature of the analysts´interpretation and to the difficulties of obtaining concurring ground and image data. They suggest that classification metrics that can compare sample distributions were slightly superior for labelling purposes but this could not be confirmed statistically. R ´ESUM ´E MAGSIC est un système a ̀ vocation opérationnel en développement dédie ́ a ̀ la classification guidée de la glace de mer pour des
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 distilled prediction
Teacher imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 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) | 0.000 | 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 teacher head, 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".