Abstract
This study explores the potential of text-to-image generative AI tools in supporting early-stage urban adaptation design through nature-based solutions (NBS). Focusing on Vila Velha, Brazil, five participants used these tools to visualize adaptive strategies against pluvial flooding at building, street, and city scales. Participants first generated images with basic prompts, then with technically detailed ones based on established NBS guidelines. The results revealed that while all tools could represent NBS elements conceptually, their technical accuracy and contextual responsiveness varied significantly depending on the intervention scale. The study demonstrates generative AI’s promise as a co-creative agent in resilient urban design, though limitations in ecological and functional understanding remain.
Keywords
Get full access to this article
View all access options for this article.
