GISA-new: Global Impervious Surface Area Map, 1985-2021

A 30-meter resolution global impervious surface area (ISA) dataset spanning from 1985 to 2021, named GISA-new. It was created by researchers at Wuhan University using a novel multi-temporal change detection method to reduce omission and commission errors. The dataset achieved an overall accuracy of 93.12% based on validation with over 100,000 global test samples.

Use Cases

• Tracking global urbanization dynamics based on the 37-year time series
• Assessing environmental impacts of urban sprawl based on high-resolution impervious surface data
• Validating and improving other land cover models based on the documented reduction in omission and commission errors
• Analyzing spatial patterns of mapping uncertainty based on the described hemispheric distribution of errors

Strengths

• Achieved a reported overall accuracy of 93.12%
• Reported low omission (10.50%) and commission (3.52%) errors compared to other datasets
• Covers a long temporal span from 1985 to 2021
• Validated with over 100,000 independent test samples globally

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Last update date is unknown; freshness unverified
• Row count and file size are unknown, which may limit suitability assessment

Provenance

Source

Wuhan University

Collection Method

Generated using a novel multi-temporal Continuous Change Detection and Classification (CCDC) algorithm and a multi-scale iterative method for commission removal.

Time Range

1985 to 2021

Geography

Global