Sagi ALON, Technion - Israel Institute of Technology, Israel
Avigdor GAL, Technion - Israel Institute of Technology, Israel
Dani BROITMAN, Technion - Israel Institute of Technology, Israel
Daniel CZAMANSKI , Rupin Academic Center, Israel
The spatial evolution of urban systems is the result of location decisions of households and firms. But these systems are in a constant state of flux. Urban systems’ dynamics are the result of two intertwined processes that operate at different rhythms: their physical structure and underlying social processes that, individually and jointly, impact the sustainability of urban areas. Neighborhoods are usually the minimal homogeneous geographical unit in urban areas, both regarding their physical, and social characteristics. Therefore, neighborhoods are the most appropriated scale for studying urban sustainability. The availability of big data and machine learning tools enables the study of the development of neighborhoods over time with an increasing level of detail. Using unsupervised machine learning algorithms and an extensive real-estate transaction dataset, we perform a multi-scale analysis of neighborhoods’ dynamics in England and Wales during a period of 26 years. The spatial and temporal dynamics of the resulting clusters of neighborhoods highlights the challenges faced by the whole urban system towards large scale urban sustainability. Our results suggest that processes triggered by urban inequalities may affect not only the social sustainability of cities (for example, through gentrification and displacement), but also the environmental sustainability of the whole urban system at a much larger scale. The analysis also highlights the potential of machine learning algorithms for the advance of urban science in general, and the study of sustainable urban systems in particular.
Mots clés : neighborhoods' dynamics |machine learning|big data|urban sustainability
A104663DB