High resolution satellite data and image segmentation produce accurate benthic substrate maps in clear waters of the great lakes
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract Benthic substrates are an important component of fish habitat and preferred substrates vary with species and life history traits. Understanding the location and areal extent of these substrates helps inform protection and management of fish and other aquatic species. Traditional methods of substrate mapping can require substantial effort and necessitate specialized equipment and personnel to work at and travel to sites. Satellite mapping of bottom types has been conducted in the past, though most of this work has been done in ocean systems and relatively little in freshwater. Using several permutations of input data and processing methods, we accurately map benthic substrates in the clear freshwater ecosystem of Fathom Five National Marine Park, Lake Huron, Canada. Using a novel approach, we were able to map substrate with relatively limited inputs to the model, making the method easily transferable among systems. An object-based approach to classification proved beneficial for accuracy, as was using higher resolution (< 2 m) satellite data to achieve our target accuracies. We also grouped accuracies by depth bins within the site to show that accuracy does not decrease linearly out to the maximum observable depth. Using a more limited depth range for classification results in higher overall and depth-specific accuracies, which may be beneficial when only a shallower portion of the site is necessary to map. With this model and information, accurate substrate maps for an area of interest could be developed to assist with the identification and management of aquatic habitat.
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.
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 it