Using topo-bathymetric LiDAR to map near shore benthic environments
Bibliographic record
Abstract
The Chiroptera II shallow water topo-bathymetric LiDAR sensor has been used to survey several coastal areas in Maritime Canada since 2014. In addition to the production of seamless elevation models, the green laser reflectance amplitude has been used in combination with the seabed roughness to map seagrass beds. The LiDAR is coupled with a 5 MPIX quality assurance camera and a 60 MPIX RCD30 multispectral camera (RGB+NIR). Utilizing the camera information with the LiDAR derivatives has allowed us to improve our bottom mapping capabilities and expand the number of benthic classes that can be derived. The amplitude of the green laser, 515 nm, decays exponentially with water depth. The strength of the signal is dependent on several factors including: water surface specular reflection, local incidence angle (scan angle + aircraft orientation), water column properties and the seabed material. We have developed a method to normalize the amplitude of the green laser points between flight lines. The energy of the light exponentially decays with depth and the amplitude of the signal is not scaled accordingly. We have developed an empirical method to depth normalize the amplitude image so it can be used in image classification. We will present various classification methods using the LiDAR and photo derived products to map the benthic environment. These methods include: semi-empirical, pattern recognition (maximum likelihood, k-means), machine learning such as random forest and object based segmentation. The results are validated using drop camera point based ground truth or echosounding data from a Biosonics system. We will also present research related to extracting attributes directly from the waveform of the green laser return that offers additional potential for habitat classification.
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 | 0.001 | 0.001 |
| 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) | 0.001 | 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".