AUTHOR=Ventura Daniele , Grosso Luca , Pensa Davide , Casoli Edoardo , Mancini Gianluca , Valente Tommaso , Scardi Michele , Rakaj Arnold 

TITLE=Coastal benthic habitat mapping and monitoring by integrating aerial and water surface low-cost drones

JOURNAL=Frontiers in Marine Science

VOLUME=Volume 9 - 2022

YEAR=2023

URL=https://www.frontiersin.org/journals/marine-science/articles/10.3389/fmars.2022.1096594

DOI=10.3389/fmars.2022.1096594

ISSN=2296-7745

ABSTRACT=Accurate data on community structure is a priority issue in the study of coastal habitats facing human pressures. The collection of such information is often challenging due to time and cost constraints, especially when frequent and long-term monitoring is needed. The recent development of remote sensing tools has offered a ground-breaking way to collect ecological information at a very fine scale.  In particular, Structure from Motion (SfM) photogrammetry has emerged as a non-destructive and low-cost method to obtain high-resolution mapping that can be applied in the most diverse fields of marine science, encompassing both emerged and underwater environments. Coastal mapping is often carried out using unmanned aerial vehicles (drones) equipped with consumer-grade cameras, resulting in limited information regarding underwater benthic habitats. Therefore, to achieve the precise characterisation of habitat types and species assemblages, adopting an array of several acquisition instruments becomes necessary. Within this framework, this study aims to evaluate an integrated approach between low-cost Unmanned Aerial (UAV) and surface (USV) vehicles for photogrammetric acquisition to finely map shallow benthic communities, which determine the high complexity of coastal environments. The photogrammetric outputs, including both UAV-based high (sub-meter) and USV-based ultra-high (sub-centimetre) raster products, were classified using Object-Based Image Analysis (OBIA) approaches. The application of a supervised learning method based on Support Vector Machines (SVM) classification resulted in good overall classification accuracies > 70 %, proving to be a practical and feasible tool for analysing both aerial and underwater imagery to detect various seabed cover classes, including key coastal features of ecological interest such as seagrass beds and macroalgal assemblages. We conclude that the integrated use of low-cost unmanned aerial and surface vehicles and GIS processing is an effective strategy for allowing fully remote detailed data on shallow water benthic communities.