WaterFormer-MS: A multi-stream deep learning framework for surface water segmentation from satellite imagery
- 24 September 2026
- journal article
- Published by Instituto Mexicano de Tecnologia del Agua in Tecnología y ciencias del agua
Abstract
Accurate mapping of surface water bodies is essential for dam monitoring, irrigation planning, and sustainable water resource management. Conventional methods based on spectral indices, such as NDWI, can face challenges in complex environments due to spectral ambiguity, seasonal variability, and urban or vegetated surfaces. Deep learning approaches such as U-Net and DeepLabv3+ have improved water-body segmentation; however, accurately delineating fine boundaries and detecting small water bodies remain challenging. To address these limitations, this study proposes WaterFormer-MS, a multi-stream deep learning framework for surface water segmentation from Sentinel-2 imagery. The architecture integrates spectral, geometric, and contextual information through dedicated processing streams and combines the extracted features using a convolutional fusion module enhanced with CBAM attention. This design aims to improve feature representation and support accurate water-body delineation. The proposed model was trained and evaluated using Sentinel-2 imagery from a publicly available Kaggle dataset containing diverse land-cover conditions, including urban, vegetated, and agricultural environments. At 300 epochs, WaterFormer-MS achieved an overall accuracy of 97.4%, a precision of 93.2%, a recall of 94.2%, an F1-score of 93.7%, and an IoU of 89.7%. Within the experimental framework, WaterFormer-MS achieved higher values than the other proposed variants. Comparisons with conventional NDWI-based approaches and published deep learning methods suggest competitive performance; however, these comparisons should be interpreted cautiously because datasets, preprocessing procedures, training protocols, and evaluation settings may differ. The results support the potential of the proposed framework for surface water segmentation and environmental monitoring applications in diverse remote sensing scenarios.Keywords
This publication has 27 references indexed in Scilit:
- Dual-Stream Convolutional Networks for Scalable and Precise Water Body Mapping from Multispectral Earth Observation ImageryInternational Journal of Computational Intelligence Systems, 2025
- Extraction of long time series wetland information based on Google Earth Engine and random forest algorithm for a plateau lake basin – A case study of Dianchi Lake, Yunnan Province, ChinaEcological Indicators, 2022
- Attentional Dense Convolutional Neural Network for Water Body Extraction From Sentinel-2 ImagesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022
- Lake water body extraction of optical remote sensing images based on semantic segmentationApplied Intelligence, 2022
- Water Body Identification from the Satellite Images using Color Component Analysis with Morphological Operations2021
- A self-attention capsule feature pyramid network for water body extraction from remote sensing imageryInternational Journal of Remote Sensing, 2020
- A novel water body extraction neural network (WBE-NN) for optical high-resolution multispectral imageryJournal of Hydrology, 2020
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation2018
- Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imageryInternational Journal of Remote Sensing, 2006
- The use of the Normalized Difference Water Index (NDWI) in the delineation of open water featuresInternational Journal of Remote Sensing, 1996