2020-ongoing

A [phylum] project

Beauty is a hybrid biological-technological installation featuring a bio-driven artificial intelligence system that remediates a contaminated soil ecology while generating an audio-visual composition in real-time. The work creates a situation where the fates of the contaminated soil and a group of bacterial cultures are determined by the whims of an AI that has an internal model of “beauty”. This AI builds its model by observing the cooperative pattern-forming and swarming behaviors of numerous bacterial species. Paenibacillus dendritiformis for example, produce intricate dendritic growth patterns in response to environmental conditions. They are also known to aid in the bioremediation of heavy metals and polycyclic aromatic hydrocarbons (present in motor oil, coal, etc) that are often found in soils, rivers, estuarine and coastal sediments. Currently, we are working at Coalesce: Center for Biological Arts, to isolate and modify these bacteria to express other novel (and potentially aesthetically pleasing) features (e.g. colors). Eventually, these cultures will be placed under microscopes for observation and analysis. Images of their growth, movement and newly acquired synthetic abilities will be captured using time-lapse microscopy and sent to the AI. Growth patterns, colors and spatial dynamics will be analyzed by the AI to determine how well the colonies conform to its internal model of beauty. The more beautiful the growth patterns of the cultured bacteria appear to the AI the more of the remediating solution the soil receives and the more nutrients the bacterial cultures under the microscope receive. It is known however, that these bacteria only produce their intricate patterns under environmental stressors such as lack of food and moisture. Thus the AI will also have to reduce nutrient levels and introduce stress-inducing chemicals (e.g. non-lethal concentrations of antibiotics) into the bacterial cultures. In addition, the bacteria will be genetically modified in a way that manipulates their stress-response genes to express the aforementioned “beauty enhancements”. Thus in order to properly remediate the contaminated soil, the bacteria may have to starve themselves to look beautiful for the AI. The AI will also express its “feelings” about this process via a series of evolving sound and visual patterns. It will attempt to ascertain the overall state of the colonies by clustering the growth patterns into groups which correspond to their beauty as well as their health status. These groups will correspond to different sound and visual instruments that trigger in response to the AI’s analysis. The soil will be remediated with a solution containing several bacterial species known for their remediation potential (in addition to Paenibacillus sp., Pseudomonas putida may also be used). The system will be setup to run indefinitely with an indeterminate outcome. Prints of the most beautiful bacterial patterns (as determined by the AI) will be displayed and sold to the public as mementos of the bacteria’s sacrifice and the AI’s aesthetic judgment.

Source code:

https://github.com/CoEmergenceLab/Beauty-Robot

https://github.com/CoEmergenceLab/WorldModel-VAE-RNN

Dataset formatting:

https://github.com/CoEmergenceLab/WorldModel-VAE-RNN/wiki/Dataset-formats

https://github.com/CoEmergenceLab/BeautyRated/wiki/Dataset-formats

Supported by: