Core code and synthetic examples for characterizing three-dimensional urban canopy structure in Shanghai

Abstract

This record provides author-developed core code and synthetic examples accompanying the manuscript “Characterizing three-dimensional urban canopy structure in Shanghai with spatial graph learning”. The package includes implementations for attribute-space and spatially regularized K-means, graph neural network encoders, joint graph reconstruction and clustering, prototype refinement, and selected evaluation procedures. Synthetic examples demonstrate method execution and implementation checks without distributing empirical study data. The archive contains source code, an input specification, dependency information, a synthetic-test entry point and test documentation. The full synthetic runner was tested on Windows with Python 3.10 and a CUDA-enabled PyTorch environment. Detailed requirements and execution instructions are provided in the README. This release covers core methodological implementations and synthetic demonstrations. Empirical Shanghai inputs, fitted study models and city-specific downstream analysis workflows are outside its scope. Third-party software dependencies are obtained separately from their official distributions.