Deep Learning for Marine Mammal Bioacoustics
Thomas Webber
Scottish Association for Marine Science
In Autumn (Fall) of 2024 I left sunny Scotland and headed across the Atlantic to one of the best ornithology labs in the world. On the surface, this seems like a rouge choice of labs to visit, given I specialise in marine mammal acoustics. The Cornell lab of Ornithology however is home to the K. Lisa Yang Center for Conservation Bioacoustics (https://www.birds.cornell.edu/ccb/). This centre outputs some impressive cutting-edge research surrounding the use of sound to study the ecology of vocal animals. From birds and insects, to elephants and whales. This cutting-edge research includes the use of deep learning to process enormous acoustic datasets to find animal vocalisations.
My own PhD aims to use deep learning in a similar way. The goal being to find the vocalisations of Risso’s dolphins from a large network of underwater microphones (compass-oceanscience.eu), in a dataset that would take over 10 years to listen to in real time. I came to the lab with a deep learning model I (very much a biologist) had developed, ready to test and break it with the hope of improving the model before its deployment.
I was welcomed into the centre and immediately introduced to other researchers who are interested in big marine datasets with the goal of also identifying vocalisations down to the species level. I was fortunate enough to be given access to these large datasets to compare how my model, trained on data from the north-east Atlantic performed on data from the north-west Atlantic and the north-east Pacific. Both these new datasets contain different species, and potentially different vocalisations even from the same species. I was able to learn and compare different methods in signal processing to be able to answer this seemingly simple question of what animal makes that noise.
After testing the model on new data and working with others at the lab to improve the model, I have now started running the model through its primary use case, the COMPASS dataset. While I have greatly enjoyed my dive into deep learning, I am looking forward to jumping back into using these outputs to study the ecology of Risso’s dolphins in Scottish waters.
Before I made the jump back to ecology however, I was fortunate enough to be introduced to Maha Assarzadeh based at the University of Chemnitz. Maha specialises in explaining how typically ‘black box’ deep learning models make their decisions and was able to help me apply a method known as occlusion-based saliency mapping to my own model, allowing us to gain a deeper insight into how the model works.
This was not only my first trip to Ithaca, but my first to the United States. So, when I could, I made full use of my time, making sure to do as much sightseeing as possible. I was fortunate enough to be alongside several other visiting PhD students, exploring lots of waterfalls, forests and lakes.
I am extremely grateful to the Challenger Society for their contribution to make this visit to the Cornell Lab of Ornithology possible. I have not only improved my own knowledge and the outputs for the PhD, but I have also been fortunate enough to meet some inspiring researchers, both those who are well established and those just starting out in their career.
Profile:
I am a marine ecologist with a keen interest in using acoustics to study marine mammals. Currently pursuing my PhD, my research focuses on investigating the occurrence of Risso's dolphins along the west coast of Scotland by employing passive acoustic monitoring. I am developing a deep learning classifier to detect Risso's dolphin vocalizations within a large acoustic dataset, which will enable me to model their distribution patterns. A key objective of my work is to provide policymakers with evidence-based recommendations for effective monitoring and management strategies to protect Risso's dolphins in Scottish waters.
Latest News
Workshop on the contribution of UK Arctic Ocean science to the International Polar Year 32/33
12:00 11th June – 16:00 12th June 2025: NOC Southampton (In-person with online option): Registration deadline 16th May
REGISTER HERE
Pre-meeting questionnaire (open to all)
The purpose of this workshop is for the UK Ocean Science community to discuss and then draft a prospectus document outlining the priority Arctic research questions the community would like to address during the run up to, throughout and beyond the International Polar Year 32/33. Additionally, to identify what unique strengths and technologies the UK has to help fill these knowledge gaps.
The second day of the workshop will be dedicated to writing groups, one for each of the priority research questions identified - from both the pre-meeting questionnaire (HERE) and day one discussion. By the end of the meeting, each group will have produced draft text and sourced supporting figures for the prospectus.
Post meeting, the draft will be opened for comments and suggestions from everyone, regardless of whether they were able to attend the workshop or not. It will then be shared with UK funders (UKRI, FCDO, DSIT, ARIA) and potential international programmes with whom we would like to collaborate (e.g. Arctic 2050, Norway). It will form a basis from which wider integration with terrestrial, atmospheric and cryosphere communities can be built, e.g. at the UK Arctic Science Meeting in September in Northumbria.
To ensure balanced community and ECR representation, and to ensure that the size of the writing groups is efficient and effective, if the number of registrations from individual institutes becomes overwhelming, we may contact individuals or teams and ask that each institute selects a smaller number of individuals to attend in-person. Please wait for confirmation of in-person attendance before finalising travel arrangements.
The workshop will be open to hybrid attendance and contributions on both days.
Challenger Society Council Position Vacancy
The Challenger Society for Marine Science (CSMS) are pleased to announce an exciting opportunity to support the next generation of ocean scientists and innovators. CSMS are looking for a new Council member to fill the Student Travel Awards and Stepping Stones Portfolio. The successful applicant will administer the travel and research grants available for Early Career Researchers.
The role involves:
- Receiving applications for the two schemes and responding to applicant inquiries
- Soliciting and compiling input from the rest of the Council for assessing the applications
- Communicating with successful and unsuccessful applicants for the two schemes
- Working with the Honorary Treasurer on allocating funds to successful applicants
- Following up with award winners on their reporting requirements
- Attending Council meetings four times a year (in person or online) and contributing to discussions and decision making for CSMS
The usual term for Council members is three years.
For more information about the CSMS Council, please follow this link: https://www.challenger-society.org.uk/The_Council
For more information about our Early Career Researcher grants and awards, please follow this link:
https://www.challenger-society.org.uk/Stepping_Stones
and
https://www.challenger-society.org.uk/Travel_awards
If you are interested in applying or have any questions regarding the role, please contact kathen@bas.ac.uk
NOC Association (NOCA) AGM 2025
The 14th AGM of the NOC Association will be held on Thursday 15th and Friday 16th May 2025. This free, on-line event will take place on Zoom, across two consecutive mornings, each starting at 10:00 and ending at 12:30. The agenda will focus on national capability (NC) science, ships, and autonomous vehicles, and how the community can engage. There will be an update on AtlantiS and on the new marine science scoping group. All are warmly welcome to join.
To participate, please complete your registration here.
For enquiries: Jackie Pearson, Secretary to NOCA: jfpea@noc.ac.uk