Advancing justice in a city’s complex systems using designs enabled by space

Abstract

Understanding the importance of data is crucial for realizing the full potential of AI in architectural design. Satellite images are extremely numerous, continuous, high resolution, and accessible, allowing nuanced experimentation through dataset curation. Combining deep learning with remote-sensing technologies, this study poses the following questions. Do newly available datasets uncover ideas about the city previously hidden because urban theory is predominantly Eurocentric? Do extensive and continuous datasets promise a more refined examination of datasets’ effects on outcomes? Generative adversarial networks can endlessly generate new designs based on a curated dataset, but architectural evaluation has been questionable. We employ quantitative and qualitative assessment metrics to investigate human collaboration with AI, producing results that contribute to understanding AI-based urban design models and the significance of dataset curation.

From Linear to Manifold Interpolation: Exemplifying the paradigm shift through interpolation

“…Despite the challenge of directly visualizing highdimensional spaces, dimensionality reduction or visualization techniques such as t-SNE, PCA, ICA, and feature visualization can be employed to explore and manipulate them (Can der Maaten, Laurens and Hinton, 2008;Zeiler and Fergus, 2014). We discuss these methods in more detail elsewhere (Mayrhofer-Hufnagl and Ennemoser, 2023).…”