Boreal Forest Deciduous Fraction and Canopy Cover, 1992-2015

1992 to 2015 data provides deciduous fraction and tree canopy cover at 30-meter resolution over the North American boreal domain. The dataset was derived from Landsat imagery using Random Forest regression models trained with in-situ samples from Alaska and Canada. It includes per-pixel uncertainty estimates and was developed as part of NASA's ABoVE project to capture forest composition changes.

Use Cases

• Tracking forest composition changes over time based on multi-decadal time-series data.
• Modeling carbon storage and albedo effects using deciduous fraction and canopy cover values.
• Validating regional or global vegetation models with high-resolution (30-m) geospatial data.
• Assessing the impact of disturbances or climate change on boreal forest structure.

Strengths

• Provides a long-term time series covering 23 years (1992-2015).
• Uses a validated machine learning method (Random Forest) trained with 70% of in-situ samples.
• Includes per-pixel uncertainty estimates for both derived variables.
• Offers high spatial resolution (30 meters) for detailed regional analysis.

Limitations

• Deciduous fraction values are only valid for pixels with tree canopy cover greater than 25%.
• Metadata completeness is medium; specific column names and dataset size are not provided.
• There is a conflict in reported last updated dates between platforms (2015 vs. 2026).

Provenance

Source

National Aeronautics and Space Administration (NASA), ABoVE project

Collection Method

Derived from Landsat 5, 7, and 8 surface reflectance composites using Random Forest regression models trained on in-situ samples.

Time Range

1992 to 2015

Freshness

2026-04-10 03:59:07.062252

Geography

North American boreal domain (Alaska and Canada)