Does Hyperspectral Imagery Improve Satellite-Derived Bathymetry? A Case Study from a Posidonia oceanica-Dominated Mediterranean Region
Bibliographic record
Abstract
Coastal bathymetric mapping is essential for marine conservation, navigation, and environmental management. Satellite-derived bathymetry (SDB) is a cost-effective solution to mapping bathymetry over large shallow areas. However, traditional multispectral instruments can produce poor depth estimates for several reasons, including image noise, atmospheric interference, waves and white caps, and where the seafloor-reflected signal is weak, e.g., in areas with deep water or a low-albedo seafloor. This study investigates the potential of PRISMA hyperspectral imagery to improve SDB performance. Through an iterative process, hyperspectral bands were added to a base Random Forest model, and model performance was assessed across different water pixel classes, including bright shallow substrates, seagrass, and deep water. The model’s performance was then compared to that of multispectral Landsat 8 imagery. The results demonstrated that adding hyperspectral bands to the base model improved bathymetric accuracy, particularly in deeper waters (25 m–30 m), where Mean Absolute Error decreased by 2.51 m from a 3-band to a 24-band model. However, the best-performing model was achieved using Landsat 8, resulting in a lower Mean Absolute Error (1.88 m) than the optimized 24-band PRISMA model (2.01 m). Our findings suggest that although additional hyperspectral bands can improve bathymetry estimation, multispectral imagery may still be more effective for general coastal bathymetry mapping despite its lower spectral resolution.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 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 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".