Research project NG| DeepWetlands: Quantifying water extent changes of wetlands with deep learning

In the Deep Wetlands project, we are developing a machine learning platform to monitor water extent changes in wetlands by integrating multiple data sources from satellite images, altimetry radars, and other space sensors. Wetlands are vital ecosystems for the functioning of the Earth system and necessary to achieve sustainable development. Water availability determines if wetlands can thrive and if they can deliver services to humans. However, thick vegetation mostly covers water changes, impairing their remote detection from space. Wetlands are disappearing rapidly; approximately 70% have been lost in the last 120 years.

Despite the danger that wetlands are currently facing, there is no global high-resolution assessment of wetland changes. This limits the in-depth and temporal analysis of wetlands from space. Changes in wetlands are unnoticed as most space-based technologies cannot fully account for water below vegetation and are limited to large water bodies. Our grand challenge is quantifying the wetland surface area changes on existing wetlands.

We plan to overcome this challenge in three work packages (WPs):

• WP1: We will collect and annotate a diverse dataset of wetland images across multiple world regions and climates.
• WP2: We will design an ML model that integrates optical, Synthetic-aperture radar (SAR), and Interferometric Synthetic Aperture Radar (InSAR) images to create an accurate inventory of existing wetlands.
• WP3: We will create a tool to visualize the wetland inventory and their changes in water extent over time.

The vignette image may be downloaded from the link below

Neural Network Diagram MSCA-PF.drawio (567 Kb)