Refining urban morphology: An explainable machine learning method for estimating footprint-level building height
This study bridged this gap by using random forest models to integrate the elevation, geometry and shape attributes of individual buildings, further refining those with spatial aggregation.
Oct 1, 2024
A new hierarchical analysis framework of building heights: Towards a more intuitive understanding of 3D urban structure
This article proposes a new framework to uncover the 3D urban structure. Firstly, kernel density is employed to reveal the hierarchical spatial structure of buildings and the contour tree method is improved to quantitatively measure the spatial diversity and complexity. Then, the 3D urban structure is abstracted by spatial interpolation after feature filtration. Finally, this framework is applied to the central area of Chengdu City.
Dec 28, 2023