Urban Essential Land Use and Land Cover Data for Regional to Global Scales

A PhD thesis dataset supporting a scalable mapping framework for fine-grained urban land use and land cover (LULC) characterization. The research by Ziming Li integrates multisource geospatial big data with deep learning algorithms, producing three open-access geospatial datasets (EULCC, EULUC-China 2.0, and EULUC-Globe). The dataset was last updated on 2026-05 06.

Use Cases

• Training noise-tolerant deep learning models for LULC classification based on the described framework.
• Conducting cross-regional model adaptation studies for urban mapping based on the thesis's focus.
• Fusing multimodal geospatial data (e.g., satellite imagery, OpenStreetMap) for urban characterization as mentioned in the description.
• Creating comparative urban science studies using the provided multi-scale data infrastructure (EULCC, EULUC-China 2.0, EULUC-Globe).
• Supporting environmental monitoring and urban planning tasks with fine-grained LULC maps derived from the framework.

Strengths

• Framework designed for scalable mapping from regional to global scales.
• Produces three named, open-access geospatial datasets (EULCC, EULUC-China 2.0, EULUC-Globe).
• Integrates multisource geospatial big data with deep learning algorithms.
• Last updated on 2026-05-06, indicating recent maintenance.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and file formats are unknown, which may limit suitability assessment.
• The dataset's primary purpose is to support a specific PhD thesis, which may constrain generalizability.

Provenance

Source

Ziming Li

Collection Method

Developed via a PhD research framework integrating multisource geospatial big data with intelligent algorithms.

Time Range

null

Freshness

Last updated 2026-05-06 09:19:30.

Geography

Regional to global scales, with specific focus on China (EULUC-China 2.0).