Spatial-Morphological Modeling for Multi-Attribute Imputation of Urban Blocks
This work addresses data imputation for urban planning, but it is incremental as it builds on existing methods like SpaceMatrix and combines them with standard techniques.
This study tackled the problem of reconstructing missing morphological indicators like floor space index (FSI) and ground space index (GSI) at the city block level for urban planning, by developing a spatial-morphological (SM) imputer tool that combines morphological clustering with neighborhood-based methods, resulting in superior performance compared to existing SOTA models when combined with inverse distance weighting (IDW) or spatial k-nearest neighbor (sKNN) methods.
Accurate reconstruction of missing morphological indicators of a city is crucial for urban planning and data-driven analysis. This study presents the spatial-morphological (SM) imputer tool, which combines data-driven morphological clustering with neighborhood-based methods to reconstruct missing values of the floor space index (FSI) and ground space index (GSI) at the city block level, inspired by the SpaceMatrix framework. This approach combines city-scale morphological patterns as global priors with local spatial information for context-dependent interpolation. The evaluation shows that while SM alone captures meaningful morphological structure, its combination with inverse distance weighting (IDW) or spatial k-nearest neighbor (sKNN) methods provides superior performance compared to existing SOTA models. Composite methods demonstrate the complementary advantages of combining morphological and spatial approaches.