Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

What makes a good tree? We used AI to ask birds

Jul 01, 2024 - theconversation.com
The article discusses the use of artificial intelligence (AI) and machine learning in designing artificial habitats for birds in the Molonglo region of Canberra, Australia. The region, once covered by grassy box gum woodlands, has lost over 95% of its original cover, leading to a crisis for birds and other animals that depend on old trees for habitat. The researchers have been working with the Australian Capital Territory Parks and Conservation Service to create artificial structures that mimic the features of large old trees. They used AI to understand what makes a good habitat from a bird's perspective, and then used this information to design better habitat structures.

The researchers used a process that involved data capture, predictive modelling, and iterative design. They mapped each tree using laser beams and used algorithms to identify and measure significant attributes such as orientation, size, and linking of branches. They then developed statistical models to predict bird behaviour based on long-term observations. The final designs were judged based on their potential to serve avian inhabitants rather than their resemblance to a tree from a human perspective. The researchers are currently building prototypes based on these designs and plan to conduct field testing to gather feedback from the birds. The article concludes by emphasizing the importance of including non-human stakeholders in the design process to create more inclusive and resilient environments.

Key takeaways:

  • Grassy box gum woodlands in southeastern Australia have been significantly reduced, leading to a loss of habitat for many species. Artificial structures are being created to mimic the features of large old trees in degraded environments.
  • AI and machine learning are being used to understand what makes a good habitat from an animal’s point of view, with large old trees and birds being included in the design process.
  • The researchers developed a process that involved data capture, predictive modelling and iterative design to create artificial habitats. They used laser scanning to map trees and developed statistical models to predict bird behaviour.
  • The principles of more-than-human design used in this study have broader applications for creating more inclusive and resilient environments for many different lifeforms. The researchers believe that using AI to give a voice to non-human stakeholders can lead to better solutions in which many species can live together.
View Full Article

Comments (0)

Be the first to comment!