TY - JOUR
TI - Automatic Classification of Biological Targets in a Tidal Channel using a Multibeam Sonar
AU - Cotter, E
AU - Polagye, B
T2 - Journal of Atmospheric and Oceanic Technology
AB - Multibeam sonars are widely used for environmental monitoring of fauna at marine renewable energy sites. However, they can rapidly accrue vast volumes of data, which poses a challenge for data processing. Here, using data from a deployment in a tidal channel with peak currents of 1-2 m/s, we demonstrate the data-reduction benefits of real-time automatic classification of targets detected and tracked in multibeam sonar data. First, we evaluate classification capabilities for three machine learning algorithms: random forests, support vector machines, and k-nearest neighbors. For each algorithm, a hill-climbing search optimizes a set of hand-engineered attributes that describe tracked targets. The random forest algorithm is found to be most effective — in post-processing, discriminating between biological and non-biological targets with a recall rate of 0.97 and a precision of 0.60. In addition, 89% of biological targets are correctly classified as either seals, diving birds, fish schools, or small targets. Model dependence on the volume of training data is evaluated. Second, a real-time implementation of the model is shown to distinguish between biological targets and non-biological targets with nearly the same performance as in post-processing. From this, we make general recommendations for implementing real-time classification of biological targets in multibeam sonar data and the transferability of trained models.
DA - 2020/08//
PY - 2020
VL - 37
SP - 1437
EP - 1455
UR - https://journals.ametsoc.org/view/journals/atot/37/8/jtechD190222.xml
DO - 10.1175/JTECH-D-19-0222.1
LA - English
KW - Marine Energy
KW - Tidal
ER -