Project Rationale
Marine mammals play an important role in the structure and function of ocean ecosystems and indicators of ocean health. Various anthropogenic activities adversely affect marine mammals, with 25% of species are threatened. Determining their spatiotemporal distribution and abundance is central to understanding their ecosystem role and the impact of anthropogenic threats.
Passive Acoustic Monitoring (PAM) and satellite-linked tracking (biotelemetry) are now-common methods for monitoring marine mammals. Both approaches generate large and geographically extensive datasets on marine mammal occurrence. The approaches differ in being more Lagrangian (biotelemetry) versus Eulerian (PAM); comparing and integrating data and insights from the two approaches is vital.
Marine autonomous vehicles are used to sense and understand the oceans and can be equipped with PAM devices that can be configured to record a large bandwidth of acoustic frequency facilitating a high-fidelity and complete record of the marine soundscape. Interrogating the vast datasets that are recorded by fleets of autonomous data is a current challenge. This project will, firstly, apply and further develop machine-learning techniques to identify individual species. Secondly, the project will leverage large marine mammal tracking datasets, as well as abundance and distribution predictions, to compare and integrate tracking, distribution and abundance data with PAM data.
Methodology
This project will determine the distribution and abundances of marine mammals using data from animals tracked with satellite-linked tags, and animal vocalisations recorded on acoustic sensors attached to fixed moorings and autonomous underwater vehicles.
The student will analyse animal tracking data from the Argos system using existing software implementations of Hidden Markov Models to infer locations at regular time intervals, while accounting for uncertainty in the location estimates. These regularized tracking data will be used to develop a variety of density surface models to estimate the abundance and distribution of marine mammals.
The student will apply and further develop existing software tools for analysing large acoustic datasets. After training, the student will apply machine learning techniques to enable discrimination of vocalisations from individual species using data from acoustic recorders mounted on autonomous systems and fixed buoys, with data available from both the Atlantic and Southern Ocean. These data will be compared to distribution and abundance model estimates derived from satellite-linked tracking. The student will investigate and develop methods for fusing tracking data and acoustic data for improved distribution and abundance estimation.
Training
The INSPIRE DTP programme provides comprehensive personal and professional development training alongside extensive opportunities for students to expand their multi-disciplinary outlook through interactions with a wide network of academic, research and the student will be registered at the University of Southampton and hosted at the School of Ocean and Earth Science at the National Oceanography Centre Southampton. Specific training will include attendance at courses in the Faculty of Engineering and Physical Sciences on marine acoustics, signal processing and/or machine learning. In addition, there are a wide range of masters level modules available in Oceanography at NOCS, and it would be expected that some of these modules would be taken, depending on the background of the candidate. The PhD student will benefit from Southampton’s membership of the Turing Institute which is a national focus of data science and artificial intelligence industrial/policy partners.