Cities are complex systems, whose morphological structure emerges from synergic integration between components and agents. As dynamic Complex Adaptive Systems their own structural transformation processes are largely unpredictable due to the non-linear nature of the changes. This course introduces a model-based approach able to define through an objective qualitative and quantitative representation, the state of a cities as Complex Adaptive System and their environmental, performance, with a view to possible improvement scenarios. The contemporary progress of information technology has enabled the use of sophisticated machine learning and data mining algorithms to process incredibly large amounts of data. So, the course presents, how the application of data engineering and modelling techniques combined with sophisticated methodologies for reading and transforming the built environment hold extraordinary potential for improving the environmental performance of urban systems. The final aim is to provide a deeper understanding of the morphological and socio-economic phenomena in urban areas, applying data engineering and modelling techniques to face the challenges posed by the heterogeneity and complexity of the problem at hand. By the end of the course, students will be able to study and describe - quantitatively and qualitatively - many aspects of a city as a complex system, with a clear identification of the roles played by the various sub-systems. The goal is to demonstrate that the sustainable new paradigm as promoted by the SDGs-2030 need to be addressed through an integrated, multidisciplinary, and multiscale approach embracing different fields of knowledge, from architecture, to urbanism, to ICT, to building technology.

By the end of the course, students will be able to:

- recognize the city as a complex adaptive system

- identify the role played by various subsystems

- describe quantitatively and qualitatively the structural characteristics of the city that effects its environmental performance

- to achieve a clear vision of possible integrated actions necessary to improve the urban performance, contributing to the Sustainable Development Goals.

Introduction to Conceptual Data Design (Entity-Relationship Model); Introduction to Data Mining; Case study: application of SIMBA (Systematic clustering-based Methodology to support Built environment Analysis) to support the selection of a reasonable and representative number of features for investigating the built environment Satellite images and remote sensing opportunities at urban scale (Copernicus services); urban modelling through GIS and 3D modelling software. Data preparation (extracting attributes) Overviews on IMM (Integrated Modification Methodology) a specific procedure for investigating the relationships between urban morphology and environmental performance in a context of the City seen as Complex Adaptive Systems. Urban-diagnostic-based procedures able to provide decision support tool for transformation actions aligned to the UN-SDG 2030.

none

At the end of the course students will be asked to present the results of their work, with presentations, diagrams drawings as well as a scientific paper. The evaluation of the original work and the analysis essay define the grade of the course.