Marine Debris Hotspot Analysis in Howe Sound, British Columbia
Bibliographic record
Abstract
Marine debris poses significant threats to coastal ecosystems and infrastructure, especially in semi-enclosed regions where monitoring is limited by inaccessibility and uneven population distribution. In Howe Sound, British Columbia, this study integrates remote sensing and environmental modeling to predict debris accumulation zones. Sentinel-2 satellite imagery was selected due to its high spatial resolution, broad spectral range, and frequent revisit time, which make it well-suited for capturing detailed coastal features. A neural network algorithm was used to classify six landcover types with an overall accuracy of 0.98. The classification results showed that many known debris hotspots are located near urban shorelines and within semi-enclosed bays. To simulate debris transport, river discharge and seasonal wind direction were modeled as surface movement drivers. The study area was divided into three sections to account for spatial variation in debris driving forces contribution. Hourly wind data from four weather stations were used to construct wind rose diagrams that captured seasonal changes in wind direction. The simulation identified 49 predicted debris hotspot locations. Of these, 20 overlapped with known hotspots, while 10 of the 29 newly identified hotspots are in less populated and previously underreported areas, particularly along the western shoreline. These findings demonstrate that remote sensing, when combined with physically based modeling, can overcome limitations of traditional monitoring methods and improve the identification of marine debris accumulation. This approach provides a scalable and transferable framework for supporting more targeted and proactive coastal management strategies.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".