DeepGreen: Coupling biological and Artificial Intelligence in urban design | ACADIA

A city made by humans, for both human and non-human citizens and planned by a new form of in-human intelligence.

by Claudia Pasquero and Marco Poletto

Ubiquitous computing enables us to decipher the Biosphere’s anthropogenic dimension, what the authors call the Urbansphere (Pasquero, Poletto, 2020). This machinic perspective unveils a new post-anthropocentric reality, where the impact of artificial systems on the natural Biosphere is indeed global, but their agency is no longer entirely human.

This paper explores a protocol to design the Urbansphere, or what we may call the urbanisation of the non-human, titled DeepGreen. With the development of DeepGreen the authors and their team are testing the potential to bring at the core of architectural and urban design research the interdependence of digital and biological intelligence.

This is achieved by developing a new bio-computational design workflow that enables pairing what is algorithmically drawn with what is biologically grown (Pasquero, Poletto, 2016). In other words, and more in detail, the paper will illustrate how GAN (Generative Adversarial Networks) algorithms (Radford et al. 2015) can be trained to “behave” like a Physarum Polycephalum, an unicellular organism endowed with surprising computational abilities and self-organizing behaviours that have made it popular among scientist and engineers alike (Adamatzky, 2010). (Fig.1)

The trained GAN_Physarum is deployed as an urban design technique, to test the potential of Polyclephalum intelligence in solving problems of urban re-metabolisation and in computing scenarios of urban morphogenesis within a non-human conceptual framework.