GAN-Physarum: la dérive numérique by ecoLogicStudio


Claudia Pasquero and Marco Poletto, founders of architecture and design innovation firm ecoLogicStudio are presenting their latest project GAN-Physarum: la dérive numérique within the exhibition “Réseaux-Mondes” (Worlds of Networks) that will be held at the Centre Pompidou in Paris (France) from February 23rd to April 25th, 2022.

For this project ecoLogicStudio and their team have trained a machine learning algorithm to behave like a living Slime Mould and they have asked it to depict the future of a bio-digital autonomous Paris. The new project is exhibited together with a second video “DeepGreen: Urbansphere” showing the application of the GAN-Physarum algorithm to a set of projects initiated in 2019 by the studio with UNDP (United Nations Development Programme).

Both pieces are part of “Mutations / Créations” series curated by Marie-Ange Brayer and Olivier Zeitoun and questions the place of the network in our societies, its pervasiveness as well as its dematerialization. The network is at the heart of technological change and several societal issues: surveillance, atomization of the individual, actor-network and the emergence of the global UrbanSphere.

“Against this backdrop, we are witnessing the unfolding of a post-natural history, a time when the impact of artificial systems on the natural Biosphere is indeed global, but their agency is no longer entirely human. Cities like Paris, have become co-evolving networks of biological and digital intelligence, semi-autonomous synthetic organisms,” affirms Claudia Pasquero, ecoLogicStudio co-founder; UIBK and UCL professor of biodigital architecture.

GAN-Physarum: la dérive numérique
A GAN (Generative Adversarial Network) is an algorithmic architecture that creates new generative models using deep learning methods. This powerful form of Artificial Intelligence has been trained by ecoLogicStudio’s bio-computational design team to “behave” like a Physarum Polycephalum, a single celled Slime Mould.

The trained GAN-Physarum is then sent on a computational dérive on the streets of Paris. In an AI generated video titled GAN-Physarum: La dérive numérique, it shows us how to decode and reinterpret the patterns of contemporary Paris’ urban fabric. We witness a transition from the original morphological order to an emergent distributed network of path systems. It is the blue-green, wet and living infrastructure of the city of the next millennium.

DeepGreen: Urbansphere
DeepGreen is a long-term project developed by ecoLogicStudio with UNDP (United Nations Development Programme) combining AI and big data analysis. DeepGreen aims at designing systemic cities that use their size and collective energy to offer refuge for both humans and displaced wildlife, that promote the emergence of positive microclimate, that replenish depleted water sources and that restore degraded terrains, pushing back on processes such as desertification, land erosion and contamination.

This entails innovative strategies of urban re-metabolisation. GAN-Physarum: la dérive numérique and DeepGreen question traditional planning concepts such as zone, boundary, scale, typology and program. Such outdated notions constrain the emergence of a truly systemic approach to urbanisation. Source by ecoLogicStudio.

  • Location: Réseaux-Mondes, Galerie 4, Centre Pompidou, Paris, France
  • Architect: ecoLogicStudio (Claudia Pasquero, Marco Poletto)
  • Project Team: Claudia Pasquero, Marco Poletto with Greta Ballschuh, Sheng Cao, Alessandra Poletto, Joy Boulois, Korbinian Enzinger, Oscar Villarreal
  • Academic Partners: Synthetic Landscape Lab at Innsbruck University, Urban Morphogenesis Lab at the Bartlett UCL
  • Commissioned: The United Nations Development Programme in partnership with Guatemala City
  • Exhibition period: 23 February – 25 April 2022
  • Photographs: NAARO, Courtesy of MINT LIST