Melbourne, Boxwood forests once covered millions of square kilometers in southeastern Australia, but today less than 5 percent remains. The loss of large old trees has been a crisis for many species of birds and other animals that depend on them for their habitat.
Replacing this habitat is not easy. There is no quick way to create a century-old tree.
One thing we can do is create artificial structures that mimic the characteristics of large old trees in degraded environments where the trees cannot live or are too young and small. We have been working with the Australian Capital Territory Parks and Conservation Service to do just this in the Molonglo region of Canberra. To build these artificial structures, we need to know what constitutes good habitat from an animal's point of view. And to find out, we developed ways to use artificial intelligence and machine learning to include non-human stakeholders (in this case, birds and trees) in the design process. In fact, we enlisted big old trees as lead designers and birds as insightful evaluators of their work.
Trees, birds and electricity poles.
Molonglo is home to a once thriving ecosystem that is now fragmented and damaged. Large, old trees are increasingly rare. These trees, some more than 500 years old, provide complex canopy structures that are essential for birds to nest, forage and rest. As urban development expands and old trees die, the challenge is to fill the void left by these giants.
Modified utility poles and relocated dead trees (or logs) have previously been introduced to the region as substitute habitat. These structures can provide important habitat features such as elevated perches, nest boxes, and bark that are not found in planted saplings. However, it is very difficult to understand exactly what features of a large, old tree are important to birds, limiting the value of artificial structures.
Carefully analyzing images and other data can help us discern these features. For example, we and our collaborators discovered that birds prefer small horizontal branches for perching and nesting. By studying birds, we can learn their preferences for certain features that have already been designed by trees. Our next challenge was to use this information to design better habitat structures.
We used a process that involved data capture, predictive modeling, and iterative design. AI and machine learning were indispensable for interpreting complex spatial data.
First, we map each tree by reflecting many millions of laser beams from every square centimeter of its surface to capture the tree crowns as point clouds. We then use algorithms to identify and measure meaningful attributes such as branch orientation, size, and linkage. A better understanding of birds' preferences for these attributes can inform designs of artificial replacements. Next, we developed statistical models to predict bird behavior. These models were based on long-term observations of bird interactions led by Philip Gibbons of the Australian National University. By simulating how birds might use artificial branches, we could refine our designs to better meet their needs.
Reimagining artificial habitats
To generate a variety of artificial tree crowns, we developed further algorithms. Instead of judging the resulting designs by how much they looked like a tree to human eyes, we used our model of bird behavior to discover how these structures could serve bird inhabitants. Our additional goal was to create lightweight structures that were Easy to install, reconfigure and remove. Our simulations showed that, compared to utility poles and hooks, these structures can provide a significant increase in habitat suitability.
Returning to the field
We are currently building prototypes based on our designs, but the final step in this process will be field tests to find out what the birds think. Birds can provide information about the characteristics of artificial structures through their interactions with them. These tests will help make designs even better. Design processes, even for non-human stakeholders like birds and trees, are currently dominated by human perspectives and experience. Our findings show how expanding the scope of creative input and judgment can improve the design process. The outcomes of this design process can take the form of “continuous services,” which provide shelter or other resources in a sustainable manner.
While we hope to build better artificial structures, it is important to remember that there is no true substitute for big, old trees. We must also preserve the trees we have and plant more for the future.
Wider implications for designThe more-than-human design principles we use in Canberra also have wider applications. Many environments around the world face similar challenges. By rethinking current design and planning approaches, we can create more inclusive and resilient environments for many different ways of living.
The essential change is to treat other species as innovative participants and experts in the design. Expanding on existing efforts to communicate with whales, bats and bees, this approach uses AI to incorporate information from non-human life forms to produce new and better designs.
Our case study shows how participatory approaches that include non-human beings can address human biases. As a result, we unlock a much larger range of possible designs.Fair Design
The world faces many urgent environmental crises. We need innovative and inclusive design approaches to meet this challenge. Trees are already excellent designers, just as birds are excellent judges of their work, and if we include their input we can create better “more than human” designs.
We believe that using AI to give a voice to non-human stakeholders can lead to better solutions where many species can live together. Our work in Canberra is an example of how participatory design can create more equitable and sustainable futures for all beings. (The conversation)SGP
Replacing this habitat is not easy. There is no quick way to create a century-old tree.
One thing we can do is create artificial structures that mimic the characteristics of large old trees in degraded environments where the trees cannot live or are too young and small. We have been working with the Australian Capital Territory Parks and Conservation Service to do just this in the Molonglo region of Canberra. To build these artificial structures, we need to know what constitutes good habitat from an animal's point of view. And to find out, we developed ways to use artificial intelligence and machine learning to include non-human stakeholders (in this case, birds and trees) in the design process. In fact, we enlisted big old trees as lead designers and birds as insightful evaluators of their work.
Trees, birds and electricity poles.
Molonglo is home to a once thriving ecosystem that is now fragmented and damaged. Large, old trees are increasingly rare. These trees, some more than 500 years old, provide complex canopy structures that are essential for birds to nest, forage and rest. As urban development expands and old trees die, the challenge is to fill the void left by these giants.
Modified utility poles and relocated dead trees (or logs) have previously been introduced to the region as substitute habitat. These structures can provide important habitat features such as elevated perches, nest boxes, and bark that are not found in planted saplings. However, it is very difficult to understand exactly what features of a large, old tree are important to birds, limiting the value of artificial structures.
Carefully analyzing images and other data can help us discern these features. For example, we and our collaborators discovered that birds prefer small horizontal branches for perching and nesting. By studying birds, we can learn their preferences for certain features that have already been designed by trees. Our next challenge was to use this information to design better habitat structures.
We used a process that involved data capture, predictive modeling, and iterative design. AI and machine learning were indispensable for interpreting complex spatial data.
First, we map each tree by reflecting many millions of laser beams from every square centimeter of its surface to capture the tree crowns as point clouds. We then use algorithms to identify and measure meaningful attributes such as branch orientation, size, and linkage. A better understanding of birds' preferences for these attributes can inform designs of artificial replacements. Next, we developed statistical models to predict bird behavior. These models were based on long-term observations of bird interactions led by Philip Gibbons of the Australian National University. By simulating how birds might use artificial branches, we could refine our designs to better meet their needs.
Reimagining artificial habitats
To generate a variety of artificial tree crowns, we developed further algorithms. Instead of judging the resulting designs by how much they looked like a tree to human eyes, we used our model of bird behavior to discover how these structures could serve bird inhabitants. Our additional goal was to create lightweight structures that were Easy to install, reconfigure and remove. Our simulations showed that, compared to utility poles and hooks, these structures can provide a significant increase in habitat suitability.
Returning to the field
We are currently building prototypes based on our designs, but the final step in this process will be field tests to find out what the birds think. Birds can provide information about the characteristics of artificial structures through their interactions with them. These tests will help make designs even better. Design processes, even for non-human stakeholders like birds and trees, are currently dominated by human perspectives and experience. Our findings show how expanding the scope of creative input and judgment can improve the design process. The outcomes of this design process can take the form of “continuous services,” which provide shelter or other resources in a sustainable manner.
While we hope to build better artificial structures, it is important to remember that there is no true substitute for big, old trees. We must also preserve the trees we have and plant more for the future.
Wider implications for designThe more-than-human design principles we use in Canberra also have wider applications. Many environments around the world face similar challenges. By rethinking current design and planning approaches, we can create more inclusive and resilient environments for many different ways of living.
The essential change is to treat other species as innovative participants and experts in the design. Expanding on existing efforts to communicate with whales, bats and bees, this approach uses AI to incorporate information from non-human life forms to produce new and better designs.
Our case study shows how participatory approaches that include non-human beings can address human biases. As a result, we unlock a much larger range of possible designs.Fair Design
The world faces many urgent environmental crises. We need innovative and inclusive design approaches to meet this challenge. Trees are already excellent designers, just as birds are excellent judges of their work, and if we include their input we can create better “more than human” designs.
We believe that using AI to give a voice to non-human stakeholders can lead to better solutions where many species can live together. Our work in Canberra is an example of how participatory design can create more equitable and sustainable futures for all beings. (The conversation)SGP
