Search

The weakness of global metrics for assessing the accuracy of satellite-derived bathymetry (SDB) is demonstrated and the magnitude of local accuracy variability quantified. SDB was developed for three small areas (500 m-by-1500 m) near Key West Florida (United States) that varied in depth and geomorphometric complexity. Data employed were 2016 and 2019 airborne lidar and three 2016 and four 2019 Landsat images. The modelling methodology was a widely used quasi-empirical linear regression-based approach. Local accuracy of SDB depth change – which was expected to be pronounced between 2016 and 2019 due to the occurrence of Category 5 Hurricane Irma in 2017 – was also calculated and examined. The global correlation (R2) between lidar-based depth and SDB for 2016 and 2019 varied from about 0.1 to 0.9 which produced relative (to depth) root mean square errors (RMSEs) between 5% and 25%. No image was consistently best for all three areas nor for either 2016 and 2019. SDB-based depth change was poorly correlated to the reference lidar-based depth change for all three areas. Spatial depiction of SDB accuracy showed considerable variability even within the three relatively small areas employed for 2016 and 2019 SDB depth estimates and 2016–2019 SDB depth change estimates. [ABSTRACT FROM AUTHOR]

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 R2 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. [ABSTRACT FROM AUTHOR]

To automate extraction of bathymetric soundings from lidar point clouds, two machine learning (ML1) techniques were combined with a more conventional density-based algorithm. The study area was four data "tiles" near the Florida Keys. The density-based algorithm determined the most likely depth (MLD) for a grid of "estimation nodes" (ENs). Unsupervised k-means clustering determined which EN's MLD depth and associated soundings represented ocean depth rather than ocean surface or noise to produce a preliminary classification. An extreme gradient boosting (XGB) model was fitted to pulse return metadata – e.g. return intensity, incidence angle – to produce a final Bathy/NotBathy classification. Compared to an operationally produced reference classification, the XGB model increased global accuracy and decreased the false negative rate (FNR) – i.e. undetected bathymetry – that are most important for nautical navigation for all but one tile. Agreement between the final XGB and operational reference classifications ranged from 0.84 to 0.999. Imbalance between Bathy and NotBathy was addressed using a probability decision threshold that equalizes the FNR and the true positive rate (TPR). Two methods are presented for visually evaluating differences between the two classifications spatially and in feature-space. [ABSTRACT FROM AUTHOR]

Shallow-water depth estimates from airborne lidar data might be improved by using sounding attribute data (SAD) and ocean geomorphometry derived from lidar soundings. Moreover, an accurate derivation of geomorphometry would be beneficial to other applications. The SAD examined here included routinely collected variables such as sounding intensity and fore/aft scan direction. Ocean-floor geomorphometry was described by slope, orientation, and pulse orthogonality that were derived from the depth estimates of bathymetry soundings using spatial extrapolation and interpolation. Four data case studies (CSs) located near Key West, Florida (United States) were the testbed for this study. To identify bathymetry soundings in lidar point clouds, extreme gradient boosting (XGB) models were fitted for all seven possible combinations of three variable suites—SAD, derived geomorphometry, and sounding depth. R2 values for the best models were between 0.6 and 0.99, and global accuracy values were between 85% and 95%. Lidar depth alone had the strongest relationship to bathymetry for all but the shallowest CS, but the SAD provided demonstrable model improvements for all CSs. The derived geomorphometry variables contained little bathymetric information. Whereas the SAD showed promise for improving the extraction of bathymetry from lidar point clouds, the derived geomorphometry variables do not appear to describe geomorphometry well. [ABSTRACT FROM AUTHOR]