Enhanced remote sensing of water surface elevation through fusion of Sentinel-3 altimeter data and climate variables using machine learning
(2026) p.261-272- Abstract
Accurate and continuous monitoring of inland surface water dynamics is vital for sustainable water resource management, climate impact assessment, and ecological planning. This study introduces a machine learning-based remote sensing-based data-fusion framework that improves Sentinel-3 radar altimeter (SRAL) estimations of water surface elevation (WSE) by integrating ERA5 reanalysis climate variables (precipitation, temperature, and evapotranspiration). Specifically, the Random Forest (RF) model was employed for its robustness and ability to capture nonlinear relationships among diverse geospatial variables. Using Lake Winnebago (LW, United States) as a test site and 101 Sentinel-3A observations, we designed six scenarios to evaluate... (More)
Accurate and continuous monitoring of inland surface water dynamics is vital for sustainable water resource management, climate impact assessment, and ecological planning. This study introduces a machine learning-based remote sensing-based data-fusion framework that improves Sentinel-3 radar altimeter (SRAL) estimations of water surface elevation (WSE) by integrating ERA5 reanalysis climate variables (precipitation, temperature, and evapotranspiration). Specifically, the Random Forest (RF) model was employed for its robustness and ability to capture nonlinear relationships among diverse geospatial variables. Using Lake Winnebago (LW, United States) as a test site and 101 Sentinel-3A observations, we designed six scenarios to evaluate model performance against in situ gauge records (2016-2024): (0) median SRAL WSE values alone; (1) RF with 41 virtual-station elevations only; (2-4) RF with the addition of 1climate variable at a time; and (5) RF with all 3variables. The best result RF with all 3climate inputs reduced RMSE from 0.47m (scenario 0) to 0.08m and increased R² from 13.65 % to 73.68 %. These findings underscore the dominant role of environmental variables in WSE modeling and demonstrate that fusing SRAL with ERA5 via RF can significantly enhance hydrological monitoring of small inland water bodies.
(Less)
- author
- Rezapour, Mahdis
; Valadan Zoej, Mohammad Javad
; Taheri Dehkordi, Alireza
LU
; Khesali, Elahe
; Naghibi, Amir
LU
and Hasehmi, Hossein
LU
- organization
- publishing date
- 2026
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- artificial intelligence, environmental variables, satellite radar altimetry, Sentinel-3, Water level
- host publication
- Hydrological Insights : Synergizing Groundwater Models, Remote Sensing, and AI for Water Sustainability - Synergizing Groundwater Models, Remote Sensing, and AI for Water Sustainability
- pages
- 12 pages
- publisher
- Elsevier
- external identifiers
-
- scopus:105032946530
- ISBN
- 9780443363955
- 9780443363948
- DOI
- 10.1016/B978-0-443-36394-8.00016-9
- language
- English
- LU publication?
- yes
- id
- ebb57bd7-2143-4b20-bd2f-37f24b179318
- date added to LUP
- 2026-04-23 12:47:34
- date last changed
- 2026-07-03 23:49:44
@inbook{ebb57bd7-2143-4b20-bd2f-37f24b179318,
abstract = {{<p>Accurate and continuous monitoring of inland surface water dynamics is vital for sustainable water resource management, climate impact assessment, and ecological planning. This study introduces a machine learning-based remote sensing-based data-fusion framework that improves Sentinel-3 radar altimeter (SRAL) estimations of water surface elevation (WSE) by integrating ERA5 reanalysis climate variables (precipitation, temperature, and evapotranspiration). Specifically, the Random Forest (RF) model was employed for its robustness and ability to capture nonlinear relationships among diverse geospatial variables. Using Lake Winnebago (LW, United States) as a test site and 101 Sentinel-3A observations, we designed six scenarios to evaluate model performance against in situ gauge records (2016-2024): (0) median SRAL WSE values alone; (1) RF with 41 virtual-station elevations only; (2-4) RF with the addition of 1climate variable at a time; and (5) RF with all 3variables. The best result RF with all 3climate inputs reduced RMSE from 0.47m (scenario 0) to 0.08m and increased R² from 13.65 % to 73.68 %. These findings underscore the dominant role of environmental variables in WSE modeling and demonstrate that fusing SRAL with ERA5 via RF can significantly enhance hydrological monitoring of small inland water bodies.</p>}},
author = {{Rezapour, Mahdis and Valadan Zoej, Mohammad Javad and Taheri Dehkordi, Alireza and Khesali, Elahe and Naghibi, Amir and Hasehmi, Hossein}},
booktitle = {{Hydrological Insights : Synergizing Groundwater Models, Remote Sensing, and AI for Water Sustainability}},
isbn = {{9780443363955}},
keywords = {{artificial intelligence; environmental variables; satellite radar altimetry; Sentinel-3; Water level}},
language = {{eng}},
pages = {{261--272}},
publisher = {{Elsevier}},
title = {{Enhanced remote sensing of water surface elevation through fusion of Sentinel-3 altimeter data and climate variables using machine learning}},
url = {{http://dx.doi.org/10.1016/B978-0-443-36394-8.00016-9}},
doi = {{10.1016/B978-0-443-36394-8.00016-9}},
year = {{2026}},
}