The use of radar and optical satellite imagery combined with advanced machine learning and metaheuristic optimization techniques to detect and quantify above ground biomass of intertidal seagrass in a New Zealand estuary

Seagrass provides numerous valuable ecosystem services across a wide range of climatic regions. However, in terms of area and habitat, this resource is in decline globally and there is an urgent need for accurate mapping of extant meadows and biomass to support sustainable seagrass blue carbon conservation and management. This study develops a novel method for a binary mapping of seagrass distribution and estimating seagrass above-ground biomass (AGB) by applying a suite of advanced machine learning (ML) algorithms combined with and without a metaheuristic optimization approach (particle swarm optimization–PSO) to various combinations of multispectral (Sentinel-2) and synthetic aperture radar (Sentinel-1) remote sensing data. Our results reveal that the Sentinel-1 data has potential for the binary mapping of seagrass meadows using an extreme gradient boosting (XGB) model (scores of precision (P) = 0.82, recall (R) = 0.90, and F₁ = 0.86) but is less effective at estimating AGB. The optimal method for estimation of AGB used both Sentinel-1 and Sentinel-2 imagery, the XGB model, and PSO optimization (coefficient of determination (R²) = 0.75, root mean squared error (RMSE) = 0.35, Akaike information criteria (AIC) = 24.80, Bayesian information criteria (BIC) = 44.70). Our findings contribute novel and advanced methods for seagrass detection and improvement of AGB estimation, which are fast and reliable, use open-source data and software and should be easily applicable to intertidal zones across many regions of the world.