OpenForest4D - Canopy Height Mapper (Multi-Sensor: NASA GEDI, Sentinel-1 SAR, Sentinel-2 Optical, AlphaEarth Embeddings)

2. Select Output Year
Choose the year for which you want to generate a canopy height map.

3. Advanced Settings

Advanced settings for data sources used to train and build the canopy height model.

Data Sources & Quality Filters

GEDI lidar measurements date range

Reference measurements from NASA's GEDI space lidar.

Start Date

End Date

Satellite Imagery Date Range

Sentinel-2 L2A optical imagery & Sentinel-1 SAR data used to map canopy height.

Start Date

End Date

Sentinel-2 Cloud Cover Limit:

Exclude satellite images that are more than X% covered by clouds. Lower = cleaner imagery but fewer available scenes; higher = more data but potentially noisier results.

Include Terrain Elevation

Adding digital elevation model data improves accuracy in high relief or mountainous areas.

Include landcover data (NLCD for US, ESA WorldCover elsewhere)

Helps the model distinguish forests from other vegetation types.

Include AlphaEarth Foundations satellite embeddings

Adds Google DeepMind's AlphaEarth Foundations annual embedding dataset, a 64-dimensional per-pixel representation learned from multi-source satellite imagery, as additional predictive features for the canopy height model.

Preview input data layers

Generates intermediate visualizations of the source data (GEDI, Sentinel) used.

4. Prediction Model

Choose the machine learning algorithm used to estimate canopy height.

Random Forest Regression

Histogram Gradient Boosting

Choose data-splitting method

Random (Default)

By Height Groups

By Fixed Height Bands

Generate model explainability report (shows which data inputs influenced predictions most — useful for validation and publication)

Note: Selecting this option will significantly increase processing time.

Canopy Height Mapper (Multi-Sensor: NASA GEDI, Sentinel-1 SAR, Sentinel-2 Optical, AlphaEarth Embeddings) Beta

Data Sources & Quality Filters