Christmas came early this year for MERIDIAN's data analytics team at Dalhousie University. After successfully competing in NVIDIA's Accelerated Data Science Call for Proposals, the team last week received a refurbished Titan V graphical processing unit (GPU), which will support their efforts to train deep neural network to detect and classify underwater sounds. The Titan V GPU, valued at around $3,000, is especially designed for high-performance computing and deep learning applications (as opposed to graphics and gaming uses), and will enable us to process underwater acoustic data much more efficiently and train Deep Learning models significantly faster. Indeed, Xuhui Liu, data analyst at MERIDIAN, is already using the new GPU for developing more efficient ways of training Deep Neural Network on small samples of training data.
Held every three years, Effects of Noise on Aquatic Life is a major international conference that brings together a wide spectrum of specialists from different sectors (university, industry, government, NGO), all sharing an interest in marine animals and a concern for their well-being in an underwater environment affected by human-made noise. 312 delegates from 27 countries attended this year's conference, which took place in The Hague in The Netherlands, among them four MERIDIAN team members. Yvan Simard gave a plenary talk on the effects of shipping noise on the beluga whale in the St. Lawrence estuary, while Amalis Riera reported new surprising discoveries about the sound repertoire of sablefish. Meanwhile Francis Juanes presented on human-made noise in fishery closure areas and Oliver Kirsebom gave plenary talks about MERIDIAN's Ocean Soundscape Atlas project and our efforts towards developing Deep-Learning based sound detection and classification tools. Go to the Presentation Archive to view all MERIDIAN presentations and posters for this conference.
MERIDIAN is operating at the crossroad of research, research support and information management why collaborating with and supporting key players from the different sectors is important to us. As of April 2019 the MERIDIAN Data Management team is contributing to two Portage/FRDR (Federated Research Data Repository) Working Groups; the FRDR User Experience and Training Working Group and the The FAST & the FRDR Working Group. The FRDR User Experience and Training Working Group is focusing on improving the FRDR user experience with its members expected to provide feedback to optimize the front-end design, documentation and training materials available to users. The FAST and the FRDR Working Group is not a spin-off of the successful The Fast and the Furious franchise featuring Vin Diesel as one may expect, but rather a subsidiary to Portage’s Data Discovery Expert Group tasked to map subject keywords from the Online Computer Library Center’s (OCLC) Faceted Application of Subject Terminology (FAST) to FRDR. This important exercise will not only improve the FRDR Discovery Service itself but also significantly improve the discoverability of Canadian research data.read more
MERIDIAN's data analytics team is excited to announce the first release of a software package for acoustic data analysis with neural networks. The package, named Ketos after the Ancient Greek word for whale, has been developed with a particular eye to detection and classification tasks in underwater acoustics. Ketos is written in Python and utilizes a number of powerful open-source software libraries including NumPy, HDF5, and Tensorflow. It is licensed under the GNU GPLv3 license and hence freely available for anyone to use and modify.read more
Passive acoustic monitoring (PAM) is a highly effective and cost-efficient method widely used in ecology to study animals in terrestrial and marine environments, allowing valuable data to be collected over long time periods with minimal effort. Such recorded "soundscapes" have important scientific and societal applications: The data provide scientists with a unique source of information on topics ranging from behaviour of individual animals to changes in biodiversity, while the insights gained have the potential to inform decision making on environmental and conservation issues.read more
The Fisheries and Oceans Canada Ocean and Freshwater Science Contribution Program (OFSCP) is an initiative that supports scientific research and science-related activities that align with the departmental interest areas such as fisheries, aquatic ecosystems and marine navigation (click here for more information). In September 2018, our proposed OFSCP project entitled Big data analysis and management of Canadian marine acoustic data sets (DAMMA), has successfully been funded for 3 years and will run until 2021. This funding allows us to progress individual aspects of our national partnerships, establish direct collaborations among underwater acoustics researchers, computer scientists, and data managers, as well as to promote the development of underwater acoustic data management best practice and Machine Learning based data analysis and visualization tools. As part of the project we will be planning and running a number of national workshops addressing topics such asread more
PyBaR is an informal co-working group organized by MERIDIAN, which provides students and researchers at Dal with a space to discuss data analysis problems and computational challenges related to their research. PyBaR focuses on (but is not limited to) the programming languages Python and R and is open to students and researchers at all levels and from all scientific fields.read more
On August 16 and 17, 2018, our first MERIDIAN workshop entitled “The Canadian Ocean Soundscape: Models, Tools and Integration Points” took place at the Atlantica Hotel in Halifax, Nova Scotia. It brought together members of the geographically disperse MERIDIAN team and various representatives of the Canadian ocean acoustics community.read more
It’s in ISO’s name: “International Organization for Standardization”. But when you look up some of their standards (for example, ISO 19115, which is what I’m most interested in), you often find that people are making their own extensions or modifications to these standards. What gives?read more
MERIDIAN (Marine Environmental Research Infrastructure for Data Integration and Application Network) successfully launched in November 2017. MERIDIAN is a Canada Foundation for Innovation funded multi-institutional and multi-disciplinary consortium of ocean researchers, computer and data management professionals. Our team members are based at Dalhousie University in Nova Scotia, the University of Victoria, University of British Columbia and Simon Fraser University, all located in British Columbia, as well as the Université du Québec à Rimouski in Québec. For more information about our team please visit ‘Meet our team’.read more