Boulders on the seabed in coastal marine environments provide key geo- and ecosystem functions and services. They serve as natural coastal protection by dissipating wave energy, and they form an important hard substrate for macroalgae, and hence for coastal marine reefs that serve as important habitats for fish. The aim of this study was to investigate the possibility of developing an automated method to classify boulders from topo-bathymetric LiDAR data in coastal marine environments. The Rødsand lagoon in Denmark was used as study area. A 100 m × 100 m test site was divided into a training and a test set. The classification was performed using the random forest machine learning algorithm. Different tuning parameters were tested. The study resulted in the development of a nearly automated method to classify boulders from topo-bathymetric LiDAR data. Different measure scores were used to evaluate the performance. For the best parameter combination, the recall of the boulders was 57%, precision was 27%, and F-score 37%, while the accuracy of the points was 99%. The most important tuning parameters for boulder classification were the subsampling level, the choice of the neighborhood radius, and the features. Automatic boulder detection will enable transparent, reproducible, and fast detection and mapping of boulders.

Stones on the seabed in coastal marine environments form an important hard substrate for macroalgae, and hence for coastal marine reefs. Such reef areas constitute important ecosystem services, e.g. storage of organic carbon in macroalgae or “blue carbon” as well as important habitats to fish for living, hiding and feeding. Information and knowledge about stone locations and geometry in coastal marine environments are often obtained as part of seabed habitat mapping. Usually, seabed habitat mapping is based on geophysical surveys using multibeam echo sounding along with side-scan sonar imaging in combination with biological ground-truthing. However, coastal areas are challenging to map with full spatial coverage due to the shallow water conditions. Furthermore, the research vessels often have too large drafts to sail in very shallow water close to the coastline. An alternative is to use airborne LiDAR technology. Topo-bathymetric LiDAR (green wavelength of 532 nm) has made it possible to derive high-resolution data of the bathymetry in coastal zones (e.g. Andersen et al., 2017). This technology can cover the transition zone between land and water, and the time consumption for data acquisition is small compared to vessel borne methods. However, the processing of the data still requires manual decision steps, which makes it rather time consuming, and to some extent subjective.The aim of this study was to investigate the possibility of developing an automated method to classify stones from topo-bathymetric LiDAR data in coastal marine environments with shallow water (<6 m). The Rødsand lagoon in Denmark, where topo-bathymetric LiDAR data were acquired in 2015, was used as test. The classification was done using the random forest machine learning algorithm. The study resulted in the development of a nearly automated method to classify stones from topo-bathymetric LiDAR data. The classification accuracy was between 80 and 90% for the test site. The obtained knowledge about stone locations can provide important information about the ecosystem services and improved management of the coastal marine environment. Acknowledgement:This work is part of the project "ECOMAP - Baltic Sea environmental assessments by opto-acoustic remote sensing, mapping, and monitoring", supported by BONUS (Art 185), funded jointly by the EU and the Innovation Fund Denmark. ReferencesAndersen MS, Gergely A, Al-Hamdani Z, Steinbacher F, Larsen LR, Ernstsen VB (2017). Processing and performance of topobathymetric lidar data for geomorphometric and morphological classification in a high-energy tidal environment. Hydrology and Earth System Sciences, 21: 43-63, DOI: 10.5194/hess-21-43-2017.

Detailed maps of the seabed and knowledge of its habitats are critical for a wide range of tasks, such as sustainable development, and environmental protection. Boulders on the seabed form an important environment for ecosystems, but the detection of them is challenging. In this study, we aim to improve the understanding of boulder predictors and to determine connections between predictors and boulder environments on different spatial scales. The Relief-F filter feature selection algorithm was used on four 30 m × 30 m areas in Rødsand lagoon, containing one boulder each, to determine the most relevant predictors. The predictors could be divided into four groups detecting different boulder characteristics: colour contrast, height, boulder boundaries, and spherical geometry. Twelve different types of boulder environments were evaluated. Bare, spherical boulders on sandy seabeds can be predicted from all four predictor groups. It is not possible to detect non-spherical boulders on seabed covered by vegetation. The best predictors for boulder detection depend on the shape and size of the boulder and the surrounding sediment and vegetation. The predictors were evaluated on a larger 400 × 2500 m area. When up-scaling the boulder detection area, larger seabed structures may affect the results. Therefore, knowledge about these structures can be used to remove errors and uncertainties from machine learning input data.