Discretization of the Urban and Non-Urban Shape: Unsupervised Machine Learning Techniques for Territorial Planning

Abstract

One of the goals of the scientific community is to equip the discipline of spatial planning with efficient tools to handle huge amounts of data. In this sense, unsupervised machine learning techniques (UMLT) can help overcome this obstacle to further the study of spatial dynamics. New machine-learning-based technologies make it possible to simulate the development of urban spatial dynamics and how they may interact with ecosystem services provided by nature. Modeling information derived from various land cover datasets, satellite earth observation and open resources such as Volunteered Geographic Information (VGI) represent a key structural step for geospatial support for land use planning. Sustainability is certainly one of the paradigms on which planning and the study of past, present and future spatial dynamics must be based. Topics such as Urban Ecosystem Services have assumed such importance that they have become a prerogative on which to guide the administration in the difficult process of transformation, taking place not only in the urban context, but also in the peri-urban one. In this paper, we present an approach aimed at analyzing the performance of clustering methods to define a standardized system for spatial planning analysis and the study of associated dynamics. The methodology built ad hoc in this research was tested in the spatial context of the city of L’Aquila (Abruzzo, Italy) to identify the urbanized and non-urbanized area with a standardized and automatic method.