Green Unified Scenarios: Change in Complexity
Part.1
This is the first of a series of posts on a framework and software that we have built within the TreesAI project. In these posts, we would like to highlight our underlying thinking. More detailed descriptions of the models and validation exercises are in our peer-reviewed journal article. In a nutshell, we aim to create a set of tools for practitioners and researchers so that they can design a new urban forest or explore the impact of an existing one with the ability to estimate each ecosystem service, such as air-pollution removal or flood risk reduction.
How a digital forest can help the real forest?
Trees have always been around us, but our relationships with trees have stayed pretty much the same. Apart from being a shelter, friend, or resource, trees are a critical part of urban infrastructure. Yet, the lack of understanding of the ecosystem benefits they provide stands in the way of them being conceived and implemented as such. It’s time to help trees help us. In this post, we explain how we help trees to grow better.
In the growth process of an urban forest, trees are not the sole actors — our built environment, policies and interventions can all affect the growth of an urban forest. Such complexity requires us to approach practices of planning and maintaining urban forests — as well as estimating their impacts — through a complex systems lens. Inspired by the Cynefin framework, a conceptual framework for decision making, we developed a Green Urban Scenarios analysis (GUS) framework that aims to make a change by combining policy intervention, planning, impact forecasting, and monitoring.
In order to enable cities to design, forecast, and monitor green infrastructure portfolios and their long-term impacts, we first built a digital twin of the real forest. In this digital forest, we can conduct diverse granular computational experiments under a specific geophysical context. This allows us to simulate and thus estimate the forest’s ecosystem benefits under varying weather conditions, maintenance regimes, species compositions, spatial distributions, and their exposure to diseases.
Above all, digitizing a forest starts with collecting data from the real forest. Digital representations of trees can be created by using a combination of datasets such as earth observations from space, street view images, field surveys, and qualitative descriptions of typologies within existing and future projects. From these data points, we create agents and abstractions for autonomous, reactive, and proactive information-processing entities such as trees, bees, birds, or sensors that collect data on soil health. By configuring agents and their interactions within the surrounding ecosystem, we model a forest as a complex system with its components and interactions within a geophysical context.
Once the digital forest is built, the health of tree populations and their ecosystem services are observed under various scenarios with different levels of maintenance and species composition. Under respective scenarios, we report CO2 emissions, carbon sequestration, water retention capacity, avoided water runoffs, and air pollution removal. Soon, we will be looking into bio-diversity, heat-island effect and mental-health co-benefits as well. By using machine learning and statistical models, we calibrate biomass growth patterns and carbon release schemes.
After all, these simulations can help people to make better decisions relevant to urban forests. By creating would-be worlds, exploring alternative counterfactuals, and performing what-if scenarios, the framework helps urban planners and city governments to make more efficient and informed policy decisions. For example, in cases where the benefits of an urban forest far exceed its costs, it provides a compelling argument for maintaining the forest. In this way, we can invest more into the forest and generate more carbon, water, health, energy, economic, and social benefits.
In the next posts, we will further explain how our framework digitizes an urban forest and maintains its modelling transparency.
Lucidminds AI
We would like to thank our TreesAI team members for their feedback on this blog piece.
