Distinguishing between two canopy-forming kelp species (Macrocystis sp. and Nereocystis sp.) on the central coast of British Columbia using object-based image analysis with WorldView-2 pansharpened imagery
Bibliographic record
Abstract
Canopy-forming kelp, which include giant kelp (Macrocystis integrifolia) and bull kelp (Nereocystis luetkeana) have been identified as ecologically significant species on the coast of British Columbia (BC). Giant kelp and bull kelp provide crucial habitat for multiple fish and invertebrate species, and they play a key role in nearshore nutrient and flow regimes. The spatial distribution of both kelp species is a crucial and currently missing input for marine protected area network planning and long-term ecological research. An ongoing collaboration between the Hakai Institute, based on the Central Coast of BC, and the Pacific Region of Fisheries and Oceans Canada, seeks to examine the application of satellite imagery for mapping kelp extent on the BC coast. A primary objective of this research is to determine whether object-based image analysis (OBIA) could be used to differentiate and delineate the extent of both giant and bull kelp using high resolution satellite imagery. A subset of pansharpened WorldView-2 imagery (0.5 m resolution) was selected for a region (McMullin Island group) on the Central Coast of BC where both species are known to be present. Knowledge of the region is extended via available field data and local ecological knowledge. While bull kelp and giant kelp have very similar spectral signatures (both are brown algae), they have very different morphologies. These morphological differences indicate that texture analysis would be best for species differentiation. Using recursive feature elimination, image feature variables (both spectral and textural) showed high differentiation between species. These variables were used as inputs for OBIA using eCognition software to test four scales of image segmentation and three different image classifiers. The results of our study demonstrate high classification accuracy for mapping bull and giant kelp. We obtained user's and producer's accuracies greater than 90% for both kelp species using a random forest classifier. We also observed an effect of the scale of image segmentation on the results of the classifications. Overall, these methods and results demonstrate a first and novel instance of the application of OBIA for mapping multiple co-occurring species of canopy-forming kelp. Future research will include examining the effects of tide height and geographical location as well as developing methods for modelling kelp biomass.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".