Global Rainfall Erosivity and ML-Predicted Error Layers Derived from IMERG

Global GeoTIFF products of rainfall erosivity and machine learning–predicted errors derived from IMERG V06 and V07 precipitation datasets. The dataset includes corrected erosivity and predicted error layers, each with global spatial coverage in WGS84 coordinates. It was created by Ameng Zou and last updated on 2026-05-15.

Use Cases

• Modeling soil erosion risk based on corrected global rainfall erosivity layers.
• Quantifying uncertainty in satellite-derived erosivity estimates using machine learning–predicted error layers.
• Comparing hydrological model inputs between IMERG V06 and V07 versions via the provided error layers.
• Conducting global or regional soil conservation planning based on the provided GeoTIFF data.

Strengths

• Provides global spatial coverage for all layers.
• Includes machine learning–predicted error estimates for both IMERG V06 and V07 versions.
• Dataset size is 148.5 MB, indicating a medium-scale geospatial product.
• Associated data processing workflow and model implementation are available in a GitHub repository.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Freshness should be verified as the last update date is in the future (2026-05-15).

Provenance

Source

Ameng Zou

Collection Method

Derived from IMERG V06 and V07 precipitation datasets using a machine learning framework.

Freshness

Last updated 2026-05-15 13:23:21

Geography

Global