Using Deep Learning to Quantify the Beauty of Outdoor Places
Seresinhe, C. I., Preis, T., & Moat, H. S. (2017) Royal Society Open Science, 4(7), 170170.
Our findings demonstrate how online data combined with neural networks can provide a deeper understanding of what environments we might find beautiful, and offer quantitative insights for policymakers charged with the design and protection of our built and natural environments.
Beautiful outdoor locations are protected by governments and have recently been shown to be associated with better health. But what makes an outdoor space beautiful? Does a beautiful outdoor location differ from an outdoor location that is simply natural?Here, we explore whether ratings of over 200,000 images of Great Britain from the online game Scenic-Or-Not, combined with hundreds of image features extracted using the Places Convolutional Neural Network, might help us understand what beautiful outdoor spaces are composed of.
While beautiful places do indeed contain natural features such as lakes, mountains and forest scenes, it appears that the old adage ‘natural is beautiful’ seems to be incomplete: flat and uninteresting green spaces are not necessarily beautiful, while characterful buildings and stunning architectural features can be. Particularly in urban areas, features such as ponds and trees seem to be important for city beauty, while spaces that feel closed-off or those that are too open and offer no refuge seem to be spaces that we do not rate as beautiful and do not prefer to spend time in.
We also find that a neural network can be trained to automatically identify scenic places, and that this network highlights both natural and built locations. Our findings demonstrate how online data combined with neural networks can provide a deeper understanding of what environments we might find beautiful, and offer quantitative insights for policymakers charged with the design and protection of our built and natural environments.