Feeling Nature
Measuring perceptions of biophilia across global biomes using visual AI
D.C. Lefosse (Massachusetts Institute of Technology, TU Delft - Environmental Technology and Design)
Fábio Duarte (Massachusetts Institute of Technology)
Rohit Sanatani (Massachusetts Institute of Technology)
Yuhao Kang (Massachusetts Institute of Technology)
A. van Timmeren (TU Delft - Environmental Technology and Design)
Carlo Ratti (Massachusetts Institute of Technology)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
An increasing number of studies suggest that biophilia encompasses benefits resulting from human–nature interactions. However, quantifying these effects remains challenging. Since natural features vary worldwide, this study explores whether people perceive biophilia universally or if it is influenced by local or geographical conditions. To this end, we quantify, qualify, and map biophilic perceptions (BP) across terrestrial biomes. We first surveyed 400 people in eight cities to identify urban features evoking more positive feelings via Google Street View imagery. Thereafter, survey outcomes were used to calculate specific metrics (coverage, diversity, distribution, intensity, specificity) aimed at measuring BP using a machine-learning model to detect 25 visual biophilic classes (BC). We found that people yield greater benefits from eye contact with nature-based elements within the cityscape unanimously, regardless of biome or gender. We provide AI-driven measurement tools applicable to any city globally to foster understanding and the enhancement of biophilic experiences.
help_outline