Machine learning for buildings' characterization and power-law recovery of urban metrics.

In this paper we focus on a critical component of the city: its building stock, which holds much of its socio-economic activities. In our case, the lack of a comprehensive database about their features and its limitation to a surveyed subset lead us to adopt data-driven techniques to extend our knowledge to the near-city-scale. Neural networks and random forests are applied to identify the buildings' number of floors and construction periods' dependencies on a set of shape features: area, perimeter, and height along with the annual electricity consumption, relying a surveyed data in the city of Beirut. The predicted results are then compared with established scaling laws of urban forms, which constitutes a further consistency check and validation of our workflow.

Kinetic roughening of the urban skyline.

We analyze the morphology of the modern urban skyline in terms of its roughness properties. This is facilitated by a database of 10^{7} building heights in cities throughout the Netherlands which allows us to compute the asymptotic height difference correlation function in each city. We find that in cities for which the height correlations display power-law scaling as a function of distance between the buildings, the corresponding roughness exponents are commensurate to the Edwards-Wilkinson and Kardar-Parisi-Zhang equations for kinetic roughening. Based on analogy to discrete deposition models, we argue that these two limiting classes emerge because of possible height restriction rules for buildings in some cities.