Supervised and self-supervised land-cover segmentation & classification of the Biesbosch wetlands

TL;DR

This paper develops a combined supervised and self-supervised learning approach for wetland land-cover segmentation using Sentinel-2 satellite imagery, improving accuracy and detail while addressing limited labeled data.

Contribution

It introduces a novel framework integrating SSL pretraining with autoencoders and scaling techniques for high-resolution wetland classification, along with a new curated dataset.

Findings

SSL pretraining improves accuracy from 85.26% to 88.23%.

High-resolution imagery yields sharper segmentation boundaries.

The curated dataset is publicly available for wetland classification.

Abstract

Accurate wetland land-cover classification is essential for environmental monitoring, biodiversity assessment, and sustainable ecosystem management. However, the scarcity of annotated data, especially for high-resolution satellite imagery, poses a significant challenge for supervised learning approaches. To tackle this issue, this study presents a methodology for wetland land-cover segmentation and classification that adopts both supervised and self-supervised learning (SSL). We train a U-Net model from scratch on Sentinel-2 imagery across six wetland regions in the Netherlands, achieving a baseline model accuracy of 85.26%. Addressing the limited availability of labeled data, the results show that SSL pretraining with an autoencoder can improve accuracy, especially for the high-resolution imagery where it is more difficult to obtain labeled data, reaching an accuracy of 88.23%. Furthermore, we introduce a framework to scale manually annotated high-resolution labels to medium-resolution inputs. While the quantitative performance between resolutions is comparable, high-resolution imagery provides significantly sharper segmentation boundaries and finer spatial detail. As part of this work, we also contribute a curated Sentinel-2 dataset with Dynamic World labels, tailored for wetland classification tasks and made publicly available.