Simulation-based inference advances water quality mapping in shallow coral reef environments
Bibliographic record
Abstract
Human activities are altering coral reef ecosystems worldwide. Optical remote sensing via satellites and drones can offer novel insights into where and how coral reefs are changing. However, interpretation of the observed optical signal (remote-sensing reflectance) is an ill-posed inverse problem, as there may be multiple different combinations of water constituents, depth and benthic reflectance that result in a similar optical signal. Here, we apply a new approach, simulation-based inference, for addressing the inverse problem in marine remote sensing. The simulation-based inference algorithm combines physics-based analytical modelling with approximate Bayesian inference and machine learning. The input to the algorithm is remote-sensing reflectance, and the output is the likely range (posterior probability density) of phytoplankton and suspended minerals concentrations, coloured dissolved organic matter absorption, wind speed and depth. We compare inference models trained with simulated hyperspectral or multispectral reflectance spectra characterized by different signal-to-noise ratios. We apply the inference model to in situ radiometric data ( n = 4) and multispectral drone imagery collected on the Tetiaroa atoll (South Pacific). We show that water constituent concentrations can be estimated from hyperspectral and multispectral remote-sensing reflectance in optically shallow environments, assuming a single benthic cover. Future developments should consider spectral mixing of multiple benthic cover 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 | 0.003 | 0.018 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".