Skip to main content
Article | Environmental Science

Avian solar work featured at DOE artificial intelligence workshop

Biophysical remote sensing scientist Yuki Hamada and her team presented an avian solar project at a DOE workshop on solar applications of artificial intelligence and machine learning.

Environmental Science (EVS) and Strategic Security Sciences (SSS) researchers are using edge computing and artificial intelligence (AI) to study the interactions of birds and solar energy projects. Using cameras that continuously monitor solar power facilities, the researchers are training several AI models in conjunction to detect, track, and classify bird activities throughout the day. The models will sort bird activities into six classes: fly-over, fly-through, perch on solar panel, land on ground, perch in background (trees), and collisions. The project is funded by the U.S. Department of Energy (DOE) Solar Energy Technologies Office (SETO).

This monitoring technology will improve the ability to collect a large volume of avian-solar interaction data to better understand potential avian impacts associated with solar energy facilities.

Image sequence of a bird tracked by Argonne’s AI models

People ask us, are birds flying into the solar panel?” said Yuki Hamada, a biophysical scientist in remote sensing who is the PI on the project. Maybe predators are bringing the birds there. Birds may also be using solar facilities to their own benefit. We don’t know because no one is watching 24/7. So that motivated us to develop technology to monitor bird activities in these facilities throughout the day.”

Hamada and her team were invited to participate in SETO’s workshop, Solar Applications of Artificial Intelligence and Machine Learning (ML), from October 31-November 1, 2023. One of the goals of the workshop was to provide a broader understanding of SETO-funded research that employs AI and ML elements.

The workshop also covered how researchers can use AI for solar energy-related topics including panel performance, grid efficiency, and wildlife interactions, as well as how AI can be used to reach climate change goals.

We have had an increase in interest from researchers and students about how we use AI, how we collect training data, and how our AI models work, and then more people get interested in the technical side of the project,” said Hamada.

Learn more about the AI-Enabled Avian-Solar Interaction Monitoring project and download the technical poster presented at the workshop.  

Additional scientists involved in the project include Adam Szymanski (SSS), Paul Tarpey (EVS), Andrew Ayers (EVS), Nicola Ferrier (MCS), Leroy Walston (EVS), and Heidi Hartmann (EVS).