Geovisual XAI Framework for OSM Updating Mechanisms in 88 German Cities

88 German cities with populations over 100,000 are analyzed to explain OpenStreetMap updating dynamics. The dataset and code support a framework integrating XGBoost, SHAP explainability, and clustering to identify non-linear interactions between urban characteristics. Author Chuan Chen published the repository on figshare under a CC-BY-4.0 license, last updated on 2026-05-10.

Use Cases

• Modeling spatial patterns of OpenStreetMap update activity based on urban attributes like functional intensity and population composition.
• Applying SHAP explainability to interpret how complex urban feature interactions influence geospatial machine learning predictions.
• Comparing attribute-based and XAI-based clustering to identify distinct urban updating mechanisms such as 'spatial position anchored' or 'facility decoupled'.
• Replicating a geovisual analytics pipeline for studying spatial heterogeneity in volunteered geographic information systems.

Strengths

• Focuses on 88 specific German cities with populations exceeding 100,000, providing a defined geographic scope.
• Implements a comparative methodological pipeline using both attribute-based and XAI-based clustering.
• The 485.2 MB repository includes code and data for full replication of the proposed analytical framework.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for specific modeling tasks.
• Data may reflect geographic bias inherent to the focus on large German cities.

Provenance

Source

figshare

Collection Method

Likely derived from OpenStreetMap and urban statistical data for the selected cities, processed through an XGBoost and SHAP analysis pipeline.

Freshness

Last updated 2026-05-10 17:36:08; freshness should be verified.

Geography

88 German cities with population > 100,000