Anxious Landscapes (2020)
article⁄Anxious Landscapes (2020)
abstract⁄Advances in the field of machine learning over the last decade have revolutionized artificial intelligence by providing a flexible means to build analytic, predictive, and generative models from large datasets, but the allied design disciplines have yet to apply these tools at the urban level to draw analytic insights on how the built environment might impact human health. Previous research has found numerous correlations between the built environment and both physical and mental health outcomessuggesting that the design of our cities may have significant impacts on human health. Developing methods of analysis that can provide insight on the correlations between the built environment and human health could help the allied design disciplines shape our cities in ways that promote human health. This research addresses these issues and contributes knowledge on the use of deep learning DL methods for urban analysis and mental health, specifically anxiety. Mental health disorders, such as anxiety, have been estimated to account for the largest proportion of global disease burden. The methods presented allow architects, planners, and urban designers to make use of large remotesensing datasets e.g., satellite and aerial images for design workflows involving analysis and generative design tasks. The research also contributes insight on correlations between anxiety prevalence and specific urban design featuresproviding actionable intelligence for the planning and design of the urban fabric.
|
|
| Year |
2020 |
| Authors |
Newton, David. |
| Issue |
ACADIA 2020: Distributed Proximities / Volume I: Technical Papers |
| Pages |
130-137. |
| Library link |
N/A |
| Entry filename |
anxious-landscapes |
