Monitoring seagrass meadows in Maputo Bay using integrated remote sensing techniques and machine learning

Abstract

Seagrass meadows are one of the most productive and valuable ecosystems on the planet. Monitoring seagrass meadows is essential to understand how these habitats change, and to develop better management and conservation practices. This study integrated satellite imagery from Sentinel-2 and Unmanned Aerial Vehicles (UAV) using machine learning to provide a consistent classification approach for monitoring seagrass in Maputo Bay, southern Mozambique. Sentinel-2 imagery was used to map seagrass extent and changes in Maputo Bay. The UAV systems were used to map seagrass at species level and biomass. All three algorithms tested in the ArcGIS environment could detect seagrass with high producer accuracy and Kappa coefficient. The area of seagrass in Maputo Bay decreased by 33.4 % between 1991 and 2023, with a decreasing trend of 0.48 km 2 /yr. A zonation pattern was observed for Oceana serrulata and Zostera capensis from the UAV imagery. The small and narrow leaved species ( Z. capensis ) occurred in the intertidal zone replaced by the broadleaved species ( O. serrulata ) in the subtidal. The total average aboveground biomass was 33.2 kg dry weight for the mapped area. The results of this study will guide implementation of combined satellite and UAV imagery with machine learning techniques for seagrass monitoring and restoration in Mozambique. • Seagrass meadows were successfully mapped using Sentinel-2 and UAV imagery in southern Mozambique. • UAV imagery analysis with machine learning techniques were used to map seagrass. • Extent and above-ground biomass of seagrass meadows can be monitored and accurately assessed. • This study informs management and restoration of seagrass in southern Mozambique.