A pattern recognition approach to identify biological clusters acquired by acoustic multi-beam in Kongsfjorden

Svalbard is one of the most intensively studied marine regions in the Artic; here the composition and distribution of marine assemblages are changing under the effect of global change, and marine communities are monitored in order to understand the long-term effects on marine biodiversity. In the present work, acoustic data collected in the Kongsfjorden using multi-beam technology was analyzed to develop a methodology for identifying and classifying 3D acoustic patterns related to fish aggregations. In particular, morphological, energetic and depth features were taken into account to develop a multi-variate classification procedure allowing to discriminate fish species. The results obtained from clustering suggest that from a mathematical point of view three distinct groups could be identified. The proposed approach, that allows to discriminate the acoustic patterns identified in the water column, seems promising for improving the monitoring programs of the marine resources, also in view of the ongoing climate changes.