Sentinel-2 Satellite-Derived Bathymetry with Data-Efficient Domain Adaptation

Satellite-derived bathymetry (SDB) enables the efficient mapping of shallow waters such as coastal zones but typically requires extensive local ground truth data to achieve high accuracy. This study evaluates the effectiveness of transfer learning in reducing this requirement while keeping estimatio...

Full description

Saved in:
Bibliographic Details
Main Authors: Christos G. E. Anagnostopoulos, Vassilios Papaioannou, Konstantinos Vlachos, Anastasia Moumtzidou, Ilias Gialampoukidis, Stefanos Vrochidis, Ioannis Kompatsiaris
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Journal of Marine Science and Engineering
Subjects:
Online Access:https://www.mdpi.com/2077-1312/13/7/1374
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849407049408970752
author Christos G. E. Anagnostopoulos
Vassilios Papaioannou
Konstantinos Vlachos
Anastasia Moumtzidou
Ilias Gialampoukidis
Stefanos Vrochidis
Ioannis Kompatsiaris
author_facet Christos G. E. Anagnostopoulos
Vassilios Papaioannou
Konstantinos Vlachos
Anastasia Moumtzidou
Ilias Gialampoukidis
Stefanos Vrochidis
Ioannis Kompatsiaris
author_sort Christos G. E. Anagnostopoulos
collection DOAJ
description Satellite-derived bathymetry (SDB) enables the efficient mapping of shallow waters such as coastal zones but typically requires extensive local ground truth data to achieve high accuracy. This study evaluates the effectiveness of transfer learning in reducing this requirement while keeping estimation accuracy at acceptable levels by adapting a deep learning model pretrained on data from Puck Lagoon (Poland) to a new coastal site in Agia Napa (Cyprus). Leveraging the open MagicBathyNet benchmark dataset and a lightweight U-Net architecture, three scenarios were studied and compared: direct inference to Cyprus, site-specific training in Cyprus, and fine-tuning from Poland to Cyprus with incrementally larger subsets of training data. Results demonstrate that fine-tuning with 15 samples reduces RMSE by over 50% relative to the direct inference baseline. In addition, the domain adaptation approach using 15 samples shows comparable performance to the site-specific model trained on all available data in Cyprus. Depth-stratified error analysis and paired statistical tests confirm that around 15 samples represent a practical lower bound for stable SDB, according to the MagicBathyNet benchmark. The findings of this work provide quantitative evidence on the effectiveness of deploying data-efficient SDB pipelines in settings of limited in situ surveys, as well as a practical lower bound for clear and shallow coastal waters.
format Article
id doaj-art-8fe54778935d4c90a3f93873cfa485a5
institution Kabale University
issn 2077-1312
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Journal of Marine Science and Engineering
spelling doaj-art-8fe54778935d4c90a3f93873cfa485a52025-08-20T03:36:11ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-07-01137137410.3390/jmse13071374Sentinel-2 Satellite-Derived Bathymetry with Data-Efficient Domain AdaptationChristos G. E. Anagnostopoulos0Vassilios Papaioannou1Konstantinos Vlachos2Anastasia Moumtzidou3Ilias Gialampoukidis4Stefanos Vrochidis5Ioannis Kompatsiaris6Information Technologies Institute, Centre for Research and Technology Hellas, 6th km Charilaou-Thermi, 57001 Thessaloniki, GreeceInformation Technologies Institute, Centre for Research and Technology Hellas, 6th km Charilaou-Thermi, 57001 Thessaloniki, GreeceCDXi Solutions P.C., Filikis Etaireias 12, 54621 Thessaloniki, GreeceInformation Technologies Institute, Centre for Research and Technology Hellas, 6th km Charilaou-Thermi, 57001 Thessaloniki, GreeceInformation Technologies Institute, Centre for Research and Technology Hellas, 6th km Charilaou-Thermi, 57001 Thessaloniki, GreeceInformation Technologies Institute, Centre for Research and Technology Hellas, 6th km Charilaou-Thermi, 57001 Thessaloniki, GreeceInformation Technologies Institute, Centre for Research and Technology Hellas, 6th km Charilaou-Thermi, 57001 Thessaloniki, GreeceSatellite-derived bathymetry (SDB) enables the efficient mapping of shallow waters such as coastal zones but typically requires extensive local ground truth data to achieve high accuracy. This study evaluates the effectiveness of transfer learning in reducing this requirement while keeping estimation accuracy at acceptable levels by adapting a deep learning model pretrained on data from Puck Lagoon (Poland) to a new coastal site in Agia Napa (Cyprus). Leveraging the open MagicBathyNet benchmark dataset and a lightweight U-Net architecture, three scenarios were studied and compared: direct inference to Cyprus, site-specific training in Cyprus, and fine-tuning from Poland to Cyprus with incrementally larger subsets of training data. Results demonstrate that fine-tuning with 15 samples reduces RMSE by over 50% relative to the direct inference baseline. In addition, the domain adaptation approach using 15 samples shows comparable performance to the site-specific model trained on all available data in Cyprus. Depth-stratified error analysis and paired statistical tests confirm that around 15 samples represent a practical lower bound for stable SDB, according to the MagicBathyNet benchmark. The findings of this work provide quantitative evidence on the effectiveness of deploying data-efficient SDB pipelines in settings of limited in situ surveys, as well as a practical lower bound for clear and shallow coastal waters.https://www.mdpi.com/2077-1312/13/7/1374satellite-derived bathymetrytransfer learningremote sensingMagicBathyNetU-NetSentinel-2
spellingShingle Christos G. E. Anagnostopoulos
Vassilios Papaioannou
Konstantinos Vlachos
Anastasia Moumtzidou
Ilias Gialampoukidis
Stefanos Vrochidis
Ioannis Kompatsiaris
Sentinel-2 Satellite-Derived Bathymetry with Data-Efficient Domain Adaptation
Journal of Marine Science and Engineering
satellite-derived bathymetry
transfer learning
remote sensing
MagicBathyNet
U-Net
Sentinel-2
title Sentinel-2 Satellite-Derived Bathymetry with Data-Efficient Domain Adaptation
title_full Sentinel-2 Satellite-Derived Bathymetry with Data-Efficient Domain Adaptation
title_fullStr Sentinel-2 Satellite-Derived Bathymetry with Data-Efficient Domain Adaptation
title_full_unstemmed Sentinel-2 Satellite-Derived Bathymetry with Data-Efficient Domain Adaptation
title_short Sentinel-2 Satellite-Derived Bathymetry with Data-Efficient Domain Adaptation
title_sort sentinel 2 satellite derived bathymetry with data efficient domain adaptation
topic satellite-derived bathymetry
transfer learning
remote sensing
MagicBathyNet
U-Net
Sentinel-2
url https://www.mdpi.com/2077-1312/13/7/1374
work_keys_str_mv AT christosgeanagnostopoulos sentinel2satellitederivedbathymetrywithdataefficientdomainadaptation
AT vassiliospapaioannou sentinel2satellitederivedbathymetrywithdataefficientdomainadaptation
AT konstantinosvlachos sentinel2satellitederivedbathymetrywithdataefficientdomainadaptation
AT anastasiamoumtzidou sentinel2satellitederivedbathymetrywithdataefficientdomainadaptation
AT iliasgialampoukidis sentinel2satellitederivedbathymetrywithdataefficientdomainadaptation
AT stefanosvrochidis sentinel2satellitederivedbathymetrywithdataefficientdomainadaptation
AT ioanniskompatsiaris sentinel2satellitederivedbathymetrywithdataefficientdomainadaptation