The use of autonomous surface vehicles (ASVs) for marine mammal detection is increasing. The ultimate goal is to develop a passive acoustic monitoring (PAM) system to be deployed for long durations at sea reporting back detections of cetaceans and making recordings when necessary. There are many obstacles that stand in the way of current PAM systems being deployed in their current form, or even with significant modification. One is the amount of current required which is normally supplied from solar panels. Unless the panels are impractically large, they are unable to provide the current required. Data communication is a further problem. Using the Iridium satellite network is slow and very expensive, making it near impossible to send the required large datasets over the network. Sending audio data is even more problematic given its size. Accurate detection of cetaceans and reduction of misclassifications also remains an area that requires further effort to improve the quality of output.
The project will build on current knowledge within Gardline and other institutions, with the aim of designing a system capable of detecting cetaceans from an ASV either with real-time monitoring, if within WIFI range, or by sending meaningful packets of data if using Iridium. There are multiple stages to the process:
Using suitable signal processing/machine learning tools (such as available in Labview, Mathscript or MATLAB) design detection algorithms for impulsive and tonal sounds generated by cetaceans
Monitor ambient and anthropogenic underwater noise
Development of a trigger (based on, for example, a duty cycle, manual instructions or machine learning methods) to determine when sound files are to be recorded
Embed the system on a chip or real-time OS, such as the compactRIO
Design, implementation and testing of a GUI, with possible audio feed if within WIFI range for real-time mitigation
Create a log of detections and other acoustic metrics for satellite communications.
The NexUSS CDT provides state-of-the-art, highly experiential training in the application and development of cutting-edge Smart and Autonomous Observing Systems for the environmental sciences, alongside comprehensive personal and professional development. There will be extensive opportunities for students to expand their multi-disciplinary outlook through interactions with a wide network of academic, research and industrial / government / policy partners.
The student will be registered at University of East Anglia, hosted at School of Computing Sciences in the Graphics, Vision and Speech laboratory. The student will receive specific training in all areas relevant to the project including signal and audio processing, machine learning as well as MATLAB and Python programming. The student will spend periods of time at Gardline to gain familiarisation with the audio signal data, hardware and the environmental aspects of the project.
This project has been shortlisted for funding by the NexUSS CDT.
Successful candidates who meet RCUK’s eligibility criteria will be awarded a NERC studentship. In most cases, UK and EU nationals who have been resident in the UK for 3 years are eligible for a full award. In 2016/17, the stipend was £14,296.
Lee R.R., Patricio S., Parker S. “SOFAR: A New Sound-Acquisition Software Package for Underwater Noise Monitoring”, In: Popper A., Hawkins A. (eds) The Effects of Noise on Aquatic Life II. Advances in Experimental Medicine and Biology, vol. 875, 2016.
Hood, J.D., Flogeras, D.G and Theriault, J.A., “Improved passive acoustic band-limited energy detection for cetaceans”, Applied Acoustics, vol. 106, pp. 36–41, May 2016.
Applications should be made to the University of East Anglia. The deadline for applications is 23:59 on 26 June 2017.