Spatial extent of surface canopy kelp derived from fixed-wing surveys (2025), North Coast, British Columbia, Canada
Bibliographic record
Abstract
Canopy-forming kelps are a critical component of many nearshore marine ecosystems, including those of British Columbia. Kelp forests create highly productive nearshore marine ecosystems which provide significant ecological, cultural and economic services. Unfortunately, kelp forests are highly susceptible to impacts from local, regional and global stressors (e.g. marine heatwaves, changes in herbivory, climate change) with recent observations of large declines in kelp forests at both global and regional scales. This sensitivity to stressors and environmental conditions makes them valuable sentinels of change in coastal marine environments. Therefore, monitoring the spatial distribution and extent of kelp forests is critical to understanding their natural variability and drivers of change as well as documenting the outcomes of conservation and management decisions and interventions. Since 2020, MaPP and the Hakai Institute have partnered to collect remotely sensed imagery on kelp forest distribution and interannual dynamics for the North Pacific Bioregion. This partnership work is governed by the MaPP-Hakai Coordination committee’s Terms of Reference. MaPP is implementing a Regional Kelp Monitoring Project (RKMP) to monitor the extent and condition of kelp forests across all four sub-regions in recognition of kelp’s ecological, cultural and economic importance. One goal of the RKMP is to gain a better understanding of kelp species’ distribution and abundance which relies on procuring high resolution spatial data. In 2025, Hakai collected fixed-wing imagery from the Hakai ACO for the North Coast MaPP subregion in partnership with MaPP RKMP to map the species-level distribution of kelp forests across areas identified as important by each subregion. Surveys conducted by the Hakai ACO are targeted to collect imagery during summer low tides when kelp biomass is at its highest. The high resolution of the aerial cameras permit the discrimination of different kelp species. Hakai Institute has also created a state-of-the-art AI tool which automates the detection of kelp canopy area by species, greatly reducing the time between imagery collection and data products. For more information on post processing, data quality assurance, software used, and summary of results please contact data@hakai.org
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 | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.003 | 0.005 |
| Meta-epidemiology (broad) | 0.006 | 0.001 |
| Bibliometrics | 0.000 | 0.003 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.005 | 0.004 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.005 | 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; both teacher heads agree on what is shown here.
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".