Project: Machine learning for the analysis of ambient marine noise

Key information:

Abstract: 

Identifying and distinguishing among events in the marine environment is an essential task in developing better understanding of climate change, and animal and human behaviour across 71% of the planet. Sources of ambient noise in the marine environment can be classified into natural, such as sediment flows and volcanic geo-hazards, or anthropogenic, such as ocean bottom trawling and offshore drilling. The aim of this research is to radically improve ocean observation and visualisation capabilities, both for oceanographic research and for various marine sector applications of national and strategic importance. This project is part of a wider research collaboration between the National Oceanography Centre and the University of Southampton to combine expertise in densely distributed big-data acquisition, using standard telecommunications fibre-optic cables, and machine learning and artificial intelligence techniques to characterise and automatically identify patterns in these data to aid human understanding of the environment.
The key challenges in this project stem from the volume of streaming data generated and the lack of substantial quantities of labelled signals. Through the project we aim to investigate dimensionality reduction techniques to reduce the dimensionality of high velocity data streams, as well as utilise unsupervised and semi-supervised learning methods to start to address the challenges of localisation, tracking and discrimination of key events in the marine environment.