How does an array of solar panels change a habitat? The query is complex—and increasingly vital, as solar energy plants proliferate across the US. The industry and researchers, nevertheless, currently don’t have loads of answers. Researchers on the Department of Energy’s (DOE) Argonne National Laboratory are developing technology that can assist.
Similar to in any outdoor setting where wildlife is present, a number of bird activity happens at solar facilities that humans miss. Birds feed, they mate, they nest, and unfortunately, they die. What role the panels and equipment play in these activities is commonly a mystery. Human monitoring at solar sites is restricted, and it could only reveal a lot.
“Real-time avian-solar interactions are a black hole when it comes to data,” said Misti Sporer, environmental development director for the utility company, Duke Energy, which operates greater than 65 solar plants within the U.S. “We don’t have a full picture of how birds use these sites, since the minute you place someone on the bottom, the birds fly off or they do something in response to the human surveyor.”
A 3-year project goals to let advanced cameras and artificial intelligence do the work of monitoring bird activity at solar facilities. Since spring 2020, Argonne researchers have been collecting video at solar energy sites, including one operated by Duke, and training computer algorithms to acknowledge birds within the scenes. The system can also be learning to categorise specific varieties of activities, including collisions with panels.
Argonne model detects moving objects (green boxes) and tracks their movements (blue lines). Non-bird objects (e.g., shadow and reflection) are filtered out prior to activity classification. Credit: (Image by Argonne National Laboratory).
Federal and state laws protect many species of birds and examining environmental impact is a component of compliance with those laws. Solar developers and operators often must conduct preconstruction habitat assessments and postconstruction fatality monitoring as a part of the environmental review requirements for a project. Argonne’s technology could help with that task.
“Managers do their best to attenuate negative effects of facilities using the perfect available science,” said Yuki Hamada, a remote-sensing scientist at Argonne and leader of the project. “The most effective available science can contain considerable uncertainty due to insufficient data when it comes to quality, quantity and category.”
For instance, a solar energy employee might discover a carcass on the bottom near some panels, but how the bird died is commonly unclear. One review of fatality monitoring studies at solar sites found the reason for death couldn’t be determined in greater than half the cases. One other study published in 2022 found that bird fatality rates at solar projects were often underestimated due to “low or insufficient monitoring duration.”
Argonne’s monitoring system could fill critical data gaps to assist understand the cause and magnitude of bird fatalities by collecting a considerable amount of near-real-time data that might include any collisions.
Alternatively, solar facilities may foster useful bird behaviors, and understanding more about those behaviors may lead to facility designs and practices which are bird friendly. Aspects could include the ability location, the kind and placement of kit, and what vegetation is growing nearby. The technology could also help illuminate what varieties of bird are present in the realm before and after a project is built.
“We’re actually seeing birds use the habitat for seed foraging, for what appears to be nesting behavior, and what appears to be inter- and intraspecies interaction,” said Sporer of the info coming from Argonne’s system at a Duke Energy site in Arizona. “So, I’m surprised at the quantity of bird use on the location when it comes to birds just being birds—no negative interactions.”
The Argonne technology is currently within the early stages, and far progress has been made. “A giant focus has been on collecting a number of video that we will annotate and use to coach our models,” said Adam Szymanski, an Argonne software engineer and technical lead on the project. “We’ve got also built and trained loads of the machine learning algorithms needed to discover birds within the landscape and classify activity. We’ve achieved pretty high accuracy on each those fronts.”
Within the project’s current phase, Hamada, Szymanski and the team are continuing to refine their model and display a working prototype system by spring 2023.
Amanda Klehr, a project biologist with the consulting firm DNV Energy U.S. Inc., noted that there are various open questions related to bird activity and bird deaths at solar sites, particularly when it comes to which phenomena is likely to be regional and which is likely to be widespread. The “lake effect,” for instance, where migrating birds mistake solar panels for bodies of water and collide with them, is one theory being explored, particularly with regard to the U.S. Southwest.
“The major thing that solar developers ask is, what do we want to do so far as preconstruction surveys to know whether or not there are potential risks to birds that may affect us in our region,” she said. She added that the Argonne monitoring system could be useful in her master’s degree research on the University of Massachusetts in Amherst, which focuses on how birds use solar sites within the Northeastern U.S. throughout the breeding season.
The Avian Solar Work Group, a collaboration amongst environmental groups, academics, and the solar industry, explores various research topics. The Argonne avian solar monitoring technology is gaining interest as a tool for research, siting, and operations. The power to gather more data with less time roaming facilities for humans would profit the industry on the permitting and compliance front.
“Postconstruction mortality monitoring tends to be time-intensive, labor intensive and expensive,” said Sporer. While it’s still early to say obviously, she said, with distant monitoring “we predict we might have fewer man hours and give you the chance to watch the interaction itself, slightly than the suspected result.”
Klehr noted that agencies comparable to the U.S. Fish and Wildlife Service and state environmental departments, that are charged with preserving resources around a solar site, also play a task in determining how research and monitoring occur.
“As a consultant working with operators, we generally attempt to coordinate with agencies,” she said. “On the wind energy side, there may be more of a deal with incorporating technology into monitoring. That’s a possible for solar energy as well, and agencies are seeing that in a more positive light.”
“Technology could be great but solving problems with technology requires that individuals actually use it,” Hamada said. “We sit up for validating this method further in the sector.”
After the prototype is complete in 2023, the following step can be to deploy Argonne’s system at more solar sites with industry partners.
—
This text was written by Christina Nunez for Argonne National Laboratory.
