Measuring shallow-water bathymetric signal strength in lidar point attribute data using machine learning

The goal of this work was to evaluate if routinely collected but seldom used airborne lidar metadata - 'point attribute data' (PAD) - analyzed using machine learning/artificial intelligence can improve extraction of shallow-water (less than 20 m) bathymetry from lidar point clouds. Extreme gradient boosting (XGB) models relating PAD to an existing bathymetry/not bathymetry classification were fitted and evaluated for four areas near the Florida Keys. The PAD examined include 'pulse specific' information such as the return intensity and PAD describing flight path consistency. The R-2 values for the XGB models were between 0.34 and 0.74. Global classification accuracies were above 80% although this reflected a sometimes extreme Bathy/NotBathy imbalance that inflated global accuracy. This imbalance was mitigated by employing a probability decision threshold (PDT) that equalizes the true positive (Bathy) and true negative (NotBathy) rates. It was concluded that 1) the strength of the bathymetric signal in the PAD should be sufficient to increase accuracy of density-based lidar point cloud bathymetry extraction methods and 2) ML can successfully model the relationship between the PAD and the Bathy/NotBathy classification. A method is also presented to examine the spatial and feature-space distribution of errors that will facilitate quality assurance and continuous improvement.

Automated summary

The study aimed to assess if analyzing airborne lidar metadata (PAD) using machine learning/artificial intelligence can enhance the accuracy of extracting shallow-water bathymetry from lidar point clouds. XGB models were built to relate PAD to bathymetry classification and a method was proposed to examine the distribution of errors in space and feature space.