AI Innovation by DeepSense Drives Pathway Program Success

Published March 24, 2021

Halifax, NS – The DeepSense team at Dalhousie University is making marine environmental monitoring for tidal energy projects easier, more reliable and more effective by creating customized software solutions in part of the Pathway Program – a technology development and testing initiative.

“Through the Pathway Program, expert researchers – including the members of the team at DeepSense – areidentifying and validating preferred environmental monitoring solutions for tidal energy projects,” said Alisdair McLean, Executive Director of OERA (Offshore Energy Research Association), one of the partners leading the Pathway Program. 

The DeepSense team has created Echofilter – a new software that uses artificial intelligence and machine learning methods to automate processing of environmental monitoring results from echosounders, a type of sonar that uses sound to detect fish and other marine life.

“Echofilter developed by DeepSense is now being used by our team at FORCE and we are able to run the software for a variety of hydroacoustic data sets,” said Dr. Daniel Hasselman of FORCE (Fundy Ocean Research Centre for Energy), the other Pathway Program lead. “We’ve found that Echofilter is accurate and reduces the time spent manually processing hydroacoustic fish data collected in the Bay of Fundy by approximately 50 per cent, doubling our productivity.  Better yet, Echofilter is more responsive to the dynamic range of tidal conditions we experience in the Bay of Fundy and requires far less time to manually edit prior to data export and analyses.”

Dr. Chris Whidden, assistant professor in Dalhousie University’s Faculty of Computer Science, led Echofilter’s early planning and design.

“We worked very closely with FORCE and OERA to understand their unique challenges, propose an initial design and modify that design during the project,” he said. “The first step in using machine learning to improve business processes is understanding the data and where the biggest costs and time sinks are. This can be especially challenging in the ocean economy because of specialized sensors, proprietary processing software, and unique environmental features.”

Using these insights, Dr. Scott Lowe, a postdoc in the Faculty of Computer Science at Dalhousie led in developing a deep learning model using existing data to automate this process and save the organization a significant amount of time.

“Our challenge was, can we automate that task, so the human doesn’t have to spend so long manually removing all of these bubbles from their data?” says Dr. Lowe. “Rather than being manually defined, the machine learning driven model that we trained is based on data. We trained the model by taking all those previous surveys that human experts have already annotated and asking the model to generate the same separation line around the entrained air as labelled by the human. After training, the model produces very similar separation lines as the human annotators.”

A webinar featuring a presentation by Jennifer LaPlante, Executive Director, DeepSense, and Dr. Chris Whidden, Assistant Professor, Faculty of Computer Science, Dalhousie University about the DeepSense team’s collaboration with FORCE and OERA will take place on March 25 from 1-2 p.m. ADT. Everyone is welcome to attend Automating the post-processing of noisy hydroacoustic fish surveying for monitoring tidal turbines – free registration is available here
 

About DeepSense
DeepSense is driving growth in the ocean economy through artificial intelligence, machine learning, and big data applied research, with the team’s work made possible through funding and support from Dalhousie University, the Atlantic Canada Opportunities Agency (ACOA), the Province of Nova Scotia, the Centre for Ocean Ventures and Entrepreneurship (COVE), the Ocean Frontier Institute (OFI) and IBM.
 

About FORCE
FORCE is Canada’s lead research facility for tidal stream technology, located in the Bay of Fundy. As a not-for-profit, FORCE collaborates with government, industry, academia and the public to better understand if this technology can play a safe, effective role in Canada’s energy future. Since 2009, FORCE has built electrical infrastructure to allow tidal stream devices to deliver power to the provincial grid and, in partnership with academic and research institutions, has invested more than $15 million in research, monitoring to increase understanding and scientific knowledge of the Minas Passage. 
 

About OERA
OERA (the Offshore Energy Research Association) is helping Nova Scotia move toward a more sustainable energy future by providing the unbiased information and insight needed to plan a path forward. OERA is a non-profit organization that serves as an independent and impartial knowledge and capacity builder. The organization supports economic growth in our province by exploring and assessing cleantech opportunities. The OERA team enables expert energy research with input from academia, industry, government, regulators and others. OERA’s scope encompasses all energy-related research, including onshore and offshore petroleum, cleantech and renewable energy.

 

Media contacts
DeepSense
Jennifer LaPlante
jlaplante@dal.ca

OERA
Alisdair McLean
amclean@oera.ca

FORCE
Lindsay Bennett
lindsay.bennett@fundyforce.ca