GISA-10m: Global Impervious Surface Area at 10-Meter Resolution

A global impervious surface area dataset at 10-meter resolution documents human footprints for climate and urban studies. It was produced by Xin Huang of Wuhan University using over 2.7 million Sentinel images and 58 million training samples derived from satellite maps and OpenStreetMap. The dataset achieved an overall accuracy greater than 86% on independent test samples.

Use Cases

• Modeling urban heat island effects based on global impervious surface coverage.
• Planning urban infrastructure and monitoring sprawl based on high-resolution land cover change.
• Assessing surface runoff and hydrological impacts based on the extent of artificial surfaces.
• Calibrating and validating other global land cover datasets based on the provided accuracy metrics.

Strengths

• High spatial resolution of 10 meters for global coverage.
• Training set of 58 million samples extracted from multi-source geospatial data.
• Validation reports an overall accuracy greater than 86%.
• Utilizes over 2.7 million Sentinel optical and radar images.

Limitations

• The specific year of data (likely 2016 from the file name) is not explicitly stated in the provided metadata.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and file size are unknown, which may limit suitability assessment.

Provenance

Source

Wuhan University

Collection Method

Produced via a mapping method leveraging multi-source geospatial data and training samples from satellite-derived maps and OpenStreetMap, processed on Google Earth Engine.

Geography

Global