Περιλαμβάνονται, με χρονολογική σειρά, δημοσιεύσεις στις οποίες έχουν χρησιμοποιηθεί δεδομένα από το εθνικό δίκτυο παρακολούθησης λιμνών.
Δημοσιεύσεις σε επιστημονικά περιοδικά
Perivolioti, Triantafyllia-Maria; Tompoulidou, Maria; Giourieva, Viktoria; Mouratidis, Antonios; Apostolakis, Antonios
The impact of submerged aquatic vegetation on satellite-derived bathymetry in shallow waters: an accuracy assessment Δημοσίευση σε επιστημονικό περιοδικό
In: European Journal of Remote Sensing, vol. 59, iss. 1, pp. 2667786, 2026.
Περίληψη | Σύνδεσμοι | BibTeX | Ετικέτες: lake bathymetry, Lake Trichonida, machine learning, remote sensing, Sentinel-2 imagery, vegetation bias
@article{Perivolioti31122026,
title = {The impact of submerged aquatic vegetation on satellite-derived bathymetry in shallow waters: an accuracy assessment},
author = {Triantafyllia-Maria Perivolioti and Maria Tompoulidou and Viktoria Giourieva and Antonios Mouratidis and Antonios Apostolakis},
url = {https://www.tandfonline.com/doi/full/10.1080/22797254.2026.2667786},
doi = {10.1080/22797254.2026.2667786},
year = {2026},
date = {2026-05-07},
urldate = {2026-05-07},
journal = {European Journal of Remote Sensing},
volume = {59},
issue = {1},
pages = {2667786},
abstract = {The aim of this study was to evaluate the performance of four widely used Satellite-derived Bathymetry (SDB) models (Stumpf, Lyzenga, Random Forest and XGBoost) in different scenarios of varying proportions of bare substrate and submerged aquatic vegetation in lake shallow-waters. Particularly, six scenarios were created, ranging from 0% to 100% submerged vegetation within a depth range of 0–10 m. The predictive accuracy of SDB models was assessed using an updated reference digital terrain model (DTM). The performance of the models was evaluated across multiple depth ranges and bottom types (bare substrate and submerged vegetation). Evaluation metrics included root mean square error (RMSE), mean absolute error (MAE), coefficient of determination (R²). One to one scatterplots demonstrated higher model performance in bare substrate, with R² values ranging from 0.56 to 0.63 for Stumpf/Lyzenga and 0.65–0.70 for XGBoost/Random Forest in bare substrate areas. Scenario-level CV of RMSE remained acceptable (<30%), decreasing from ~0.058 (0% vegetation) to ~0.022 (100% vegetation). Random Forest and XGBoost outperformed Lyzenga and Stumpf models under mixed scenarios. This study improves the understanding of SDB training requirements in mixed lake bottom types and offers valuable insights for improving the application of SDB in lakes.},
keywords = {lake bathymetry, Lake Trichonida, machine learning, remote sensing, Sentinel-2 imagery, vegetation bias},
pubstate = {published},
tppubtype = {article}
}
The aim of this study was to evaluate the performance of four widely used Satellite-derived Bathymetry (SDB) models (Stumpf, Lyzenga, Random Forest and XGBoost) in different scenarios of varying proportions of bare substrate and submerged aquatic vegetation in lake shallow-waters. Particularly, six scenarios were created, ranging from 0% to 100% submerged vegetation within a depth range of 0–10 m. The predictive accuracy of SDB models was assessed using an updated reference digital terrain model (DTM). The performance of the models was evaluated across multiple depth ranges and bottom types (bare substrate and submerged vegetation). Evaluation metrics included root mean square error (RMSE), mean absolute error (MAE), coefficient of determination (R²). One to one scatterplots demonstrated higher model performance in bare substrate, with R² values ranging from 0.56 to 0.63 for Stumpf/Lyzenga and 0.65–0.70 for XGBoost/Random Forest in bare substrate areas. Scenario-level CV of RMSE remained acceptable (<30%), decreasing from ~0.058 (0% vegetation) to ~0.022 (100% vegetation). Random Forest and XGBoost outperformed Lyzenga and Stumpf models under mixed scenarios. This study improves the understanding of SDB training requirements in mixed lake bottom types and offers valuable insights for improving the application of SDB in lakes.