The risk evaluation in urban sustainability: a threshold methodology and a neral network investigation

Urban sustainability is a dynamic process that lies on positive interactions among three different urban sub-systems: social, economic and physical, where social well-being coexists with economic development and environmental quality. Nevertheless in the existing cities this utopian scenario does not appear. Aestethic quality of natural and built environment is often associated to marginality and poverty, labor market variety and urban efficiency coexist with pollution, criminality and high settlement costs. In the conurbation of Milan those sub-systems combines themselves differently to form the core, the periphery and the large metropolitan area. The interactions among the over-mentioned systems are complex and unforeseable and seem to present the opportunity for a scientific investigation: based on Neural Network approach. The aim of this study is to investigate the underlying relationships among the three sub-systems, by a set of social, economic and physical attributes of the conurbation of Milan, and to verify if this underlying structure reproduces the heterogeneity of urban realities and allows distinguishing part of the town with different assets or drawbacks in sustainability. The Data Base (DB), composed by 80 indicators and 144 areal units of the city of Milan, has been processed by Self-Reflexive Neural Networks (SRNN). These Networks are an useful instrument of investigation and analogic questioning of the Data Base. Once the SRNN has learned the structure of the weights from the DB, by querying the network with the maximization or minimization of specific groups of attributes, is possible to read the related properties and to rank the cities performing this urban profile.