Water column compensation workflow for hyperspectral imaging data
Bibliographic record
Abstract
Our article describes a data processing workflow for hyperspectral imaging data to compensate for the water column in shallow, clear to moderate optical water types. We provide a MATLAB script that can be readily used to implement the described workflow. We break down each code segment of this script so that it is more approachable for use and modification by end users and data providers. The workflow initially implements the method for water column compensation described in Lyzenga (1978) and Lyzenga (1981), generating depth invariant indices from spectral band pairs. Given the high dimensionality of hyperspectral imaging data, an overwhelming number of depth invariant indices are generated in the workflow. As such, a correlation based feature selection methodology is applied to remove redundant depth invariant indices. In a post-processing step, a principal component transformation is applied, extracting features that account for a substantial amount of the variance from the non-redundant depth invariant indices while reducing dimensionality. To fully showcase the developed methodology and its potential for extracting bottom type information, we provide an example output of the water column compensation workflow using hyperspectral imaging data collected over the coast of Philpott's Island in Long Sault Parkway provincial park, Ontario, Canada. Workflow calculates depth invariant indices for hyperspectral imaging data to compensate for the water column in shallow, clear to moderate optical water types. The applied principal component transformation generates features that account for a substantial amount of the variance from the depth invariant indices while reducing dimensionality. The output (both depth invariant index image and principal component image) allows for the analysis of bottom type in shallow, clear to moderate optical water types.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.017 | 0.017 |
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".