Innovasea’s Tagless Fish Detection Technology Could Be Win/Win for Hydropower Industry

If the expression “shooting fish in a barrel” is meant to denote something that’s easy, the phrase “counting fish in a river” could be used to mean the exact opposite.

Utilities that produce hydropower have long known how hard it is to actually count fish. When required by permits to chronicle fish activity in and around dams and generating stations, operators have to undertake such counts and report the results to regulators. That data can ultimately impact when they can or can’t generate power.

Earlier this year Innovasea introduced a new tagless fish detection technology that could bring the tedious task of counting fish into the 21^st century. More important, it could provide a deeper understanding of how fish behave around hydro facilities so operators can both lessen their impact on wildlife and reduce the number of days they shut down or modify operations to mitigate those potential impacts.

The new technology uses a combination of optical cameras, imaging sonar and artificial intelligence to detect, count and classify fish in real time. Tested at White Rock Dam in Nova Scotia for the first time this spring, the prototype system was more than 95 percent accurate and provided unprecedented levels of intelligence to Nova Scotia Power, the owner of the dam.

“It’s been really cool. We’ve had phenomenal results,” said Jean Quirion, Innovasea’s vice president of research and development for fish tracking. “Nobody has ever recorded this kind of data before.”

Counting Alewife

The 70-year-old White Rock Dam is on the Gaspereau River in northern Nova Scotia. In late spring it often shuts down its 3.4 megawatt generating station so as not to harm the enormous schools of alewife that come barreling up the river to spawn in its headwaters.

Like most utilities, it relies on manual counting from recorded video to determine when the migration activity has slowed down.

In 2020 Innovasea partnered with Nova Scotia Power and DeepSense to develop a better way of monitoring the alewife migration. The partnership was part of the Innovasea-led Ocean Aware project being overseen by Canada’s Ocean Supercluster.

After two years of work behind the scenes, the prototype AI system was ready for its trial run at White Rock this spring. One optical camera was installed at the top of the fish ladder, and the other in the fish bypass. Two sonar cameras were installed upstream and downstream from the dam.

Once the system was up and running, data was sent to the cloud and could be accessed in real time via an Innovasea app that showed the rate of fishing passing by each minute, the cumulative total of fish and a live camera image that gets refreshed every 60 seconds.

The Results

In all, the AI-powered system, which monitored the busy spawning period between mid-April and late June, counted nearly a million fish – 918,169 to be exact.

Most interesting, the data indicated two distinct phases of the alewife migration.

In the first phase, which ended around May 18, the sonar and IP cameras discovered that all the fish were going up the fish ladder and turning left to swim upstream to spawn. In the second phase, the fish were more erratic, swimming all over the place.

“The data resolution we got was amazing,” said Quirion. “Before this people were manually counting fish from recorded video, and there’s no way they could produce this same level of data because they don’t have time to watch video 24/7 and notice every fish.”

More Data, Deeper Knowledge

In addition, the data showed that the alewife prefer being on the move during the daytime.

“You can clearly see the day/night patterns,” said Quirion. “During the day time, the fish are very active, with hundreds of fish passing by per minute at certain times. This happens in the morning, at mid-day and then late in the day before sundown. And then the activity dies off at night and they’re inactive.”

Those kinds of insights, coming in real time, hold the potential to make hydropower facilities more precise in how they operate – halting power generation when fish are nearby but minimizing downtime when the fish aren’t active. Rather than shut down for days or weeks, for example, operators could run overnight and stop at dawn when fish are on the move again.

Validating the Data

The final results from the AI system were validated against the results from manual counting. During 178 random samplings, Innovasea personnel counted 2,564 fish from recorded video while the tagless detection system counted 2,681, a difference of less than 5 percent.

The fish counting was supplemented by an acoustic telemetry study of 300 alewife who were tagged with Innovasea’s V3 transmitters on May 7 and 8. While the results are still being analyzed, the study confirmed that the tagged fish all headed upstream during the first phase of the migration.

Eventually that study will show the precise movement patterns of all 300 fish to add an extra layer of information for Nova Scotia Power to ponder.

More Field Trials

While the results from White Rock have been promising, Innovasea is looking to perform additional field trials of the system with other utilities or dam operators.

“We’re actively looking for sites where we can continue to refine this promising technology,” said Aaron Legge, group product manager at Innovasea. “We’re hoping to find additional partners who are interested in being able to both optimize their power generation and protect important species – while also making it much easier for them to meet their regulatory requirements.”

Of particular interest in the next round of trials is seeing how the AI system performs identifying different species of fish. That’s something it wasn’t required to do at White Rock, which sees almost exclusively alewife using its fish passage systems.

Visit our Tagless Fish Detection Trial Program page to learn more about beta testing opportunities.