Semantic urban river space delineation and typology

Abstract

The urban river space is the area in the city surrounding a river, distinguishing itself from other parts of the city by this relationship with the water. Urban river spaces around the world are increasingly under development and being regenerated. Urban planning solutions necessitate a comprehensive overview of this space, their boundaries and their characteristics. However, the concept of the urban river space is ambiguously defined, with varying definitions across studies. This thesis addresses the need for a standardized approach through semantic urban river space delineation to facilitate cross-case analysis. Three delineation methods are proposed and applied to urban areas in the Netherlands: the first building line based on visible building nodes, the visible space derived from viewshed analysis, and the floodable area, based on 100-year flood depth data. As urban river spaces are often represented as cross-sectional segments in research, this segment is used as unit to develop a typology of urban river spaces in the Netherlands. Properties of the segment, such as elevation, landuse, vegetation, flood risk, and visibility are quantified and used as input for the k-means clustering algorithm. 10 clusters are derived, each representing a semantic type of river space, resulting in a data-driven typology that enhances the understanding of urban river spaces in the Netherlands.