Building a mangrove ecosystem monitoring tool for managers using Sentinel-2 imagery in Google Earth Engine

Mangroves are among the most productive ecosystems worldwide, providing numerous ecological and socioeconomic co-benefits. Though highly adapted to fluctuating environmental conditions, increasing disturbances from climate change and human activities have caused significant losses. With increasing environmental uncertainties, adaptive management is necessary to monitor and evaluate changes, and to understand drivers of mangrove decline. Effective management requires access to accurate, current, and multitemporal data on mangrove cover, but such data is often lacking or inaccessible to managers. We present mangrove cover maps for Puerto Rico, the U.S. Virgin Islands, and the British Virgin Islands for the years 2020, 2021, and 2022. We used the Random Forest machine learning technique in Google Earth Engine (GEE) to classify Sentinel-2 multispectral imagery (MSI) and created mangrove vegetation maps at 10 m resolution, with classification accuracies greater than 85%. We host and present the maps in an easy-to-use GEE decision support tool (DST) for managers and policy makers that allows for evaluation of change over time. We also provide a mapping workflow fully implemented in GEE that allows for the production of subsequent maps with minimal technical expertise required. The DST and mapping workflow can help users to detect impacts of disturbances on mangrove vegetation and to monitor progress of conservation interventions such as rehabilitation or legal protection. Furthermore, our mapping approach differentiates between intact and degraded mangrove vegetation, and the increased spatial resolution of Sentinel-2 MSI imagery allowed us to capture mangrove patches that had not been previously mapped by studies using coarser resolution imagery. Our assessment of mangrove cover change between years indicated patterns of loss and recovery likely associated with disturbances, natural recovery and/or human driven restoration.