Automatic classification and mapping of the seabed using airborne LiDAR bathymetry

Abstract

Shallow coastal areas are among the most inhabited areas and are valuable for biodiversity, recreation and the economy. Due to climate change and sea level rise, sustainable management of coastal areas involves extensive exploration, monitoring, and protection. Current high-resolution remote sensing methods for monitoring these areas include bathymetric LiDAR. Therefore, this study presents a novel methodological approach to assess the suitability of Airborne LiDAR Bathymetry for automatic classification and mapping of the seafloor. Nine classes of geomorphological bedforms and three classes of anthropogenic structures were identified. They were automatically mapped by Geographic Object-Based Image Analysis and machine learning supervised classifiers. The developed method was applied to six study sites and a 48 km submerged coastal zone in the Southern Baltic, achieving an overall accuracy of up to 94%. This study shows that calculation of the Multiresolution Index of Ridge Top Flatness (secondary feature) can be used to quickly and automatically determine sandbar crests and ridge tops. The methodical approach developed in this study can help evaluate and protect other shallow coastal environments and coastal protection structures.