eSPACE: Emergency spatial pre-SCAT for Arctic Coastal Ecosystem
Bibliographic record
Abstract
The eSPACE project (emergency Spatial Pre-SCAT for Arctic Coastal Ecosystems; SCAT: Shoreline Cleanup and Assessment Technique) is focused on developing capacity to enhance our state of preparedness for emergencies in the event of an oil spill in Canada's North. Baseline coastal information is required for operational prioritization, coordination of on-site spill response activities and wildlife management. Earth Observation data from satellites such as RADARSAT-2 can potentially be used to identify and map shoreline characteristics, coastal habitats and resources at risk. The commonly used shoreline mapping method consists of manual interpretation of oblique videos to segment and classify existing shoreline vectors (based on 1:50k maps). In the summers of 2010, 2011 and 2012, geotagged video imagery was collected along the coastline for six selected pilot sites in the Arctic. RADARSAT-2 data was simultaneously acquired over these sites. An object-based classification scheme was developed using RADARST-2 data, SPOT-4/-5 optical data as well as ancillary data such as a digital elevation model. This paper presents the general methods used for all eSPACE sites, however only the results for the Richards Island pilot site are presented and discussed. Using ground observation data for validation, the classification reached an overall accuracy of 75% for Richards Island. Although the vectors produced from the standard method carry more information on the substrate types and on-site accessibility, the object-based classification allows for a spatial representation (area) of the shoreline classes as opposed to a line (vector), and the representation of all the shoreline types, not only the ones covered by the helicopter surveys. As well, given the vastness of Canada's Arctic region, manual interpretation of the shorelines won't be feasible.
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 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.013 | 0.006 |
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".