A Full Cloud-Native Dive into Bioregional-Scale Seagrass Mapping in the Mediterranean using Sentinel-2 Multitemporal Data

Kurzfassung

The seagrass Posidonia oceanica is the main habitat-forming species of the coastal Mediterranean, providing millennia-scale ecosystem services including habitat provisioning, biodiversity maintenance, food security, coastal protection, and carbon sequestration. Yet, projected temperature extremes and sea level rise due to climate change, the current knowledge gaps in its basin-wide extent, and its slow growth increase the risk of reduction and loss of these wide-scope services. As a result, accurate and efficient mapping of its distribution and trajectories of change is needed. Here, we leverage recent advances in Earth Observation—cloud computing, open satellite data, and machine learning—and field observations through a cloud-native geoprocessing framework to estimate the pan-Mediterranean extent of P. oceanica species. Employing 279,186 Sentinel-2 images taken between 2015 and 2019, and a human-labeled training dataset of 62,928 pixels, we map 19,020 km2 of P. oceanica meadows up to 25 m of depth in 22 Mediterranean countries, across a total seabed area of 56,783 km2. Using 2,480 independent, field-based points, we observe an overall accuracy of 72%. Given suitable reference data, our highly-scalable cloud-native framework can provide effective and data-driven seagrass mapping products to timely support pertinent Multilateral Environmental Agreements—from national to continental and global scale.