Parametric Mapping and Machine Learning. Experimental Tool to analyse Landscape in Slow Mobility Paths

The bottom-up research developed has led to an evolution in terms of tools and methodologies for spatial representation, divided into three classes. The first one implements the GIS digital ecosystem for spatial data provision. The first is inherent in the parametric precision landscape modeling using NURBS technology in synergy with parametric platforms. The multiscalar flexibility of the ad hoc developed workflow was applied both to manage soft mobility nodes and to define energy flows in built-up areas of fragile territories. The second concerns the quantitative analysis of the quality of slow routes through programming codes that guide artificial intelligence platforms such as Mapillary and Google TensorFlow. At present, research is directed towards the synergic fusion of the two classes to have increasingly precise representation and analysis tools.