Monitoring mangrove traits through optical Earth observation: Towards spatio-temporal scalability using cloud-based Sentinel-2 continuous time series.

[Display omitted] • Retrieval of key mangrove traits based on Sentinel-2 surface reflectance data. • Gaussian Processes Regression (GPR) was trained on PROSAIL simulations and active learning intelligent sampling techniques. • GPR model gives insight in the most relevant bands and delivers per-pixel uncertainty interval. • Optimal GPR models were implemented in Google Earth Engine for end-user mapping over space and time. • Time series gap-filling via Whittaker smoothing enabled temporal decomposition to monitor mangrove trait dynamics. As mangrove forests are facing escalating threats from anthropogenic and natural stressors, Earth observation capabilities are providing an unprecedented view of these vital ecosystems. This study aimed to leverage the extensive archive and continuous stream of Sentinel-2 (S2) data and its integration into cloud-computing platforms to map key mangrove traits, indicative of ecosystem health and resilience. Specifically, a hybrid retrieval model implemented in Google Earth Engine (GEE) was operationalized for quantitative estimation of multiple mangrove traits from S2. For this purpose, the leaf-to-canopy radiative transfer model (RTM) PROSAIL in synergy with non-parametric Gaussian Processes Regression (GPR) were selected for hybrid retrieval models of effective Leaf Area Index (LAI e), Leaf Chlorophyll Content (C a b ), Leaf Water Thickness (C w), and Leaf Dry Matter (C m). GPR models were trained and optimized with a PROSAIL-based simulated dataset in combination with active learning sampling techniques to reduce the training dataset towards the most informative samples. Validation against in situ measurements showed high accuracy models achieved for LAI e ( R 2 = 0.693, NRMSE = 12.03 %) and Cab ( R 2 = 0.689, NRMSE = 13.29 %), while moderate performances were obtained for Cm ( R 2 = 0.597, NRMSE = 16.37 %) and Cw ( R 2 = 0.442, NRMSE = 16.66 %). The GPR models were subsequently implemented into GEE for processing of a time series data stream ranging from 2019 to 2023, together with the cloud-gap filling by applying a Whittaker smoother. Seamless maps of four key mangrove traits were generated simultaneously with per-pixel uncertainty estimation. The entire GEE-based workflow enables time series decomposition to uncover trends and seasonal dynamics. Supported by field validation, this study demonstrates a scalable approach for spatiotemporal monitoring of key mangrove traits using hybrid retrieval models via GEE implementation. These advances may contribute to national-scale monitoring in Vietnam and beyond to support mangrove ecosystem protection efforts and management thereof. [ABSTRACT FROM AUTHOR]