English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In intensively managed forests in Europe, where forests are divided intostands of small size and may show heterogeneity within stands, a high spatialresolution (10 - 20 meters) is arguably needed to capture the differences incanopy height. In this work, we developed a deep learning model based onmulti-stream remote sensing measurements to create a high-resolution canopyheight map over the "Landes de Gascogne" forest in France, a large maritimepine plantation of 13,000 km$^2$ with flat terrain and intensive management.This area is characterized by even-aged and mono-specific stands, of a typicallength of a few hundred meters, harvested every 35 to 50 years. Our deeplearning U-Net model uses multi-band images from Sentinel-1 and Sentinel-2 withcomposite time averages as input to predict tree height derived from GEDIwaveforms. The evaluation is performed with external validation data fromforest inventory plots and a stereo 3D reconstruction model based on Skysatimagery available at specific locations. We trained seven different U-netmodels based on a combination of Sentinel-1 and Sentinel-2 bands to evaluatethe importance of each instrument in the dominant height retrieval. The modeloutputs allow us to generate a 10 m resolution canopy height map of the whole"Landes de Gascogne" forest area for 2020 with a mean absolute error of 2.02 mon the Test dataset. The best predictions were obtained using all availablesatellite layers from Sentinel-1 and Sentinel-2 but using only one satellitesource also provided good predictions. For all validation datasets inconiferous forests, our model showed better metrics than previous canopy heightmodels available in the same region.

High-resolution canopy height map in the Landes forest (France) based on GEDI, Sentinel-1, and Sentinel-2 data with a deep learning approach