UniGCA: Urban Growth Simulation Data for Raster and Vector Models

A 10.7 MB document authored by Xiaoyu Chen describes the UniGCA framework for urban growth simulation. The framework integrates raster- and vector-based cellular automata models using a graph-based approach. Case studies demonstrating the framework's application include Shanghai, China, and the Pine Catchment in Australia.

Use Cases

• Benchmarking urban growth model accuracy based on the reported Figure of Merit (FoM) improvements.
• Developing universal simulation frameworks based on the described graph-based cellular automata (UniGCA) approach.
• Simulating large-scale urban expansion based on the Partitioned Graph U-Net Cellular Automata (PGUN-CA) model architecture.
• Comparing raster- and vector-based simulation paradigms based on the unified framework's described capabilities.

Strengths

• Framework validated with case studies in Shanghai and Pine Catchment, Australia.
• Reported accuracy improvements of 6.96% and 9.41% in Figure of Merit (FoM) over baseline models.
• Released under a CC-BY-4.0 license, permitting broad reuse.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data may reflect geographic bias inherent to the two specific case study locations.

Provenance

Source

Xiaoyu Chen via figshare

Collection Method

Likely contains simulation outputs and model descriptions from the proposed UniGCA framework.

Freshness

Last updated 2026-05-15 04:59:26; freshness should be verified.

Geography

Shanghai, China and Pine Catchment, Australia