Monitoring water reservoirs extent with Segment Anything Model applied to Sentinel imagery

Water reservoirs are an essential resource for human health, natural ecosystems, and socio-economic activities, making their effective monitoring mandatory for informed decision-making on sustainable water management. Particularly important is monitoring the extent and level, which enable determinat...

Full description

Saved in:
Bibliographic Details
Main Authors: G. Sergi, F. Bocchino, R. Ravanelli, M. Crespi
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:European Journal of Remote Sensing
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/22797254.2025.2527248
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850117902417526784
author G. Sergi
F. Bocchino
R. Ravanelli
M. Crespi
author_facet G. Sergi
F. Bocchino
R. Ravanelli
M. Crespi
author_sort G. Sergi
collection DOAJ
description Water reservoirs are an essential resource for human health, natural ecosystems, and socio-economic activities, making their effective monitoring mandatory for informed decision-making on sustainable water management. Particularly important is monitoring the extent and level, which enable determination of volume variations. In this respect, this work investigates the performance of Segment Anything Model (SAM) – a foundation model for segmentation released by Meta AI Research – in segmenting water bodies from medium-resolution satellite imagery. SAM was applied in its original form to Sentinel-1 and Sentinel-2 images through prompt engineering (seed modality), testing five different 3-band combinations of the input images in two areas of the Ligurian coast (Italy). Overall, the study demonstrates the adaptability and efficiency of SAM in segmenting water bodies. Among the tested configurations, the SAR 3-band combination achieved the best performance, with [Formula: see text] scores ranging from 0.874 to 0.994. Furthermore, SAM performs better in simpler scenarios with uniform radiometric properties and regular water boundaries, achieving [Formula: see text] score close to 1 with seeds in any position within the water body. Conversely, in more complex scenarios, accurate seed prompt placement becomes critical; analysis of [Formula: see text] maps revealed that seeds placed near the edge of the water, where sharp gradients occur, significantly improve SAM segmentation performance.
format Article
id doaj-art-32b232338fda451ea8500df868e8f708
institution OA Journals
issn 2279-7254
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series European Journal of Remote Sensing
spelling doaj-art-32b232338fda451ea8500df868e8f7082025-08-20T02:36:00ZengTaylor & Francis GroupEuropean Journal of Remote Sensing2279-72542025-12-0158110.1080/22797254.2025.2527248Monitoring water reservoirs extent with Segment Anything Model applied to Sentinel imageryG. Sergi0F. Bocchino1R. Ravanelli2M. Crespi3Department of Civil, Building and Environmental Engineering (DICEA), Geodesy and Geomatics Division - Sapienza University of Rome, Rome, ItalyDepartment of Civil, Building and Environmental Engineering (DICEA), Geodesy and Geomatics Division - Sapienza University of Rome, Rome, ItalyGeomatics Unit, Department of Geography, University of Liège, Liège, BelgiumDepartment of Civil, Building and Environmental Engineering (DICEA), Geodesy and Geomatics Division - Sapienza University of Rome, Rome, ItalyWater reservoirs are an essential resource for human health, natural ecosystems, and socio-economic activities, making their effective monitoring mandatory for informed decision-making on sustainable water management. Particularly important is monitoring the extent and level, which enable determination of volume variations. In this respect, this work investigates the performance of Segment Anything Model (SAM) – a foundation model for segmentation released by Meta AI Research – in segmenting water bodies from medium-resolution satellite imagery. SAM was applied in its original form to Sentinel-1 and Sentinel-2 images through prompt engineering (seed modality), testing five different 3-band combinations of the input images in two areas of the Ligurian coast (Italy). Overall, the study demonstrates the adaptability and efficiency of SAM in segmenting water bodies. Among the tested configurations, the SAR 3-band combination achieved the best performance, with [Formula: see text] scores ranging from 0.874 to 0.994. Furthermore, SAM performs better in simpler scenarios with uniform radiometric properties and regular water boundaries, achieving [Formula: see text] score close to 1 with seeds in any position within the water body. Conversely, in more complex scenarios, accurate seed prompt placement becomes critical; analysis of [Formula: see text] maps revealed that seeds placed near the edge of the water, where sharp gradients occur, significantly improve SAM segmentation performance.https://www.tandfonline.com/doi/10.1080/22797254.2025.2527248Water reservoir extent monitoringCopernicus sentinelsfoundation modelssegment anything model
spellingShingle G. Sergi
F. Bocchino
R. Ravanelli
M. Crespi
Monitoring water reservoirs extent with Segment Anything Model applied to Sentinel imagery
European Journal of Remote Sensing
Water reservoir extent monitoring
Copernicus sentinels
foundation models
segment anything model
title Monitoring water reservoirs extent with Segment Anything Model applied to Sentinel imagery
title_full Monitoring water reservoirs extent with Segment Anything Model applied to Sentinel imagery
title_fullStr Monitoring water reservoirs extent with Segment Anything Model applied to Sentinel imagery
title_full_unstemmed Monitoring water reservoirs extent with Segment Anything Model applied to Sentinel imagery
title_short Monitoring water reservoirs extent with Segment Anything Model applied to Sentinel imagery
title_sort monitoring water reservoirs extent with segment anything model applied to sentinel imagery
topic Water reservoir extent monitoring
Copernicus sentinels
foundation models
segment anything model
url https://www.tandfonline.com/doi/10.1080/22797254.2025.2527248
work_keys_str_mv AT gsergi monitoringwaterreservoirsextentwithsegmentanythingmodelappliedtosentinelimagery
AT fbocchino monitoringwaterreservoirsextentwithsegmentanythingmodelappliedtosentinelimagery
AT rravanelli monitoringwaterreservoirsextentwithsegmentanythingmodelappliedtosentinelimagery
AT mcrespi monitoringwaterreservoirsextentwithsegmentanythingmodelappliedtosentinelimagery