The Oak Ridge National Laboratory Distributed Active Archive Center (ORNL DAAC) has released a new Level 4C Global Waveform Structural Complexity Index (WSCI) fusion data product from the Global Ecosystem Dynamics Investigation (GEDI). This dataset provides global estimates of WSCI at 25-meter spatial resolution with 3-monthly temporal frequency from 2015 to 2022.
The product advances the sparse footprint-level GEDI L4C product by using deep learning to fuse spaceborne lidar observations with multi-sensor Synthetic Aperture Radar (SAR) data, producing spatially continuous estimates of three-dimensional forest structural complexity.
GEDI is a full-waveform lidar instrument aboard the International Space Station (ISS) that collects high-resolution laser ranging measurements of Earth’s vertical structure. The instrument uses three lasers to produce eight beam ground transects, sampling ~25m footprints spaced approximately every 60m along-track. Beam transects are spaced approximately 600m apart in the cross-track direction, resulting in an across-track width of ~4.2 km. GEDI’s precise measurements of canopy height, vertical structure, and surface elevation greatly advance our understanding of forest ecosystems, carbon and water cycling, biodiversity, and habitat structure.
For this dataset, the team employed an adapted EfficientNet version 2 architecture that integrates Sentinel-1 C-band, ALOS-2 PALSAR-2 L-band SAR mosaics, and Copernicus Digital Elevation Model data. Each 25-meter pixel contains the mean WSCI estimate, along with quantified uncertainties (aleatoric and epistemic standard deviations) and data quality indicators. Model training included approximately 133 million GEDI footprints collected between 51.6 degrees North and 51.6 degrees South from April 2019 to December 2022, with predictions extending the record both temporally (2015-2022) and spatially (beyond GEDI's latitude limits) through the fusion approach.
The GEDI Level 4C Global WSCI fusion dataset is distributed in cloud-optimized GeoTIFF (COG) format and is available through NASA Earthdata Search, Earthdata Cloud, and the data landing page. doi:10.3334/ORNLDAAC/2474
If you have questions, please contact ORNL DAAC user services or visit NASA Earthdata Forum.
Data Resources
Related publication
de Conto, T., Armston, J. and Dubayah, R., 2026. Scalable deep fusion of spaceborne lidar and synthetic aperture radar for global forest structural complexity mapping. Machine Learning: Earth, 2(1), p.015002. doi:10.1088/3049-4753/ae2c01