Digitally and computational power meets biological matter and processes for new perspectives on interactions with our natural environment.
Team & Collaboration
Helene Steiner, studio99 Artist in Residence at Microsoft Research from Aug. – Dec. 2015 Paul Johns, Senior Research Developer at Microsoft Research Sidhant Gupta, Research Scientist at Microsoft Research Jonathan Lester, Researcher at Microsoft Research Chris Meek, Natural Language Researcher at Microsoft Research Asta Roseway, Research Designer at Microsoft Research
Nature has its own language; specifically, plants use electro-chemical signals to communicate their needs. Project Florence is a speculative glimpse into our Future where both our Natural and Digital worlds could co-exist in harmony through enhanced communication. Combining Natural Language Research, Biology, Design, and Engineering… we have created the first instantiation of a plant to human interface through the power of language. Project Florence is the creation of Helene Steiner (Artist in Residence, Microsoft Research).
Plants synthesize a very large amount of information via electrical and chemical signals and deliberately make changes to themselves, their neighbors and the land nearby for their benefit. This signals caused by cell depolarization through ions fluxes such as K + , Ca2 + , H + , Na + , and Cl alert the whole plant for localized stimuli, such as biotic and abiotic stress and are one of the most universal properties of living organisms. In project Florence we take advantage of the sensibility of plants to different light frequencies and use it to trigger a plant response through manipulation and compare the similarities between plants and natural language processes.
The electrical plant responses can be measured at the tissue and whole plant level with the help of attached electrodes to the plant and an open source board for bioelectric signals. Project Florence approaches plants as reactive living matter which generates new perceptions towards how we interface with our natural environment. This creates the opportunity to create a rudimentary conversation with our natural environment.
In this system, the user first attempts to communicate with or influence the plant through modulated natural language. Their inputs are analyzed for sentiment and semantic content. The resulting signals are used to modulate a light source that projects onto the plant. During this conversational turn, the chemical and electrical signals from the plant and information about its environment got observed. These signals are combined with the linguistic input are used to generate a conversational response from the plant. The resulting responses are transformations of the input, driven by linguistic trees as well as lexical paraphrases. Although the plant does not fully understand the linguistic information, it influences the resulting output in novel and unpredictable ways.
Project Florence provides a base for future research and applications for environmental studies, biological sensors and gen-expressions and new opportunities for bridging our digitally and natural world through computation.