A-
A
A+

L'information grandeur nature

Centre de documentation
scientifique

Actualité

L'actu ! Horaires du CDOS

Le centre est ouvert en salle de travail du lundi au vendredi, de 08h30 à 19h00. Les prêts physiques sont suspendus pour le moment. Merci d'adr...

Consulter les archives

dernière publication

Dernière publication Consultez les parutions du CDoS

Informations pratiques

Le centre de documentation scientifique
de l'Institut est aussi celui de l'ENSG-Géomatique.

Envoyez un mail au contact ci-dessous pour vos demandes.

Contact : cdos@ign.fr

Comment venir ?
Pour se rendre au centre de documentation, se reporter au 'Plan d'accès au bâtiment' tout en bas de page à droite. Le centre se trouve dans le bâtiment de l'ENSG. On y accède par le hall, entre l'aile Cassini et l'aile Laplace.

Mots RAMEAU représentant le fonds du centre de documentation
géomatique, géodésie, réseaux (géodésie), systèmes de localisation par satellites,
imagerie satellitaire, traitement d'images, photogrammétrie, lasergrammétrie,
systèmes d'information géographique, données géospatiales, cartographie,
géographie - base de données

Nouvelle recherche

Article: Article/Communication

A CNN-based approach for the estimation of canopy heights and wood volume from GEDI waveforms / Ibrahim Fayad in Remote sensing of environment, vol 265 (November 2021)

URL article

Public

[article]
inRemote sensing of environment > vol 265 (November 2021) . - n° 112652

Titre :	A CNN-based approach for the estimation of canopy heights and wood volume from GEDI waveforms
Type de document :	Article/Communication
Auteurs :	Ibrahim Fayad, Auteur ; Dino Lenco, Auteur ; Nicolas Baghdadi, Auteur ; et al., Auteur
Année de publication :	2021
Article en page(s) :	n° 112652
Note générale :	bibliographie
Langues :	Anglais (eng)
Descripteur :	[Vedettes matières IGN] Lasergrammétrie [Termes IGN] Brésil [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] Eucalyptus (genre) [Termes IGN] forme d'onde [Termes IGN] Global Ecosystem Dynamics Investigation lidar [Termes IGN] hauteur des arbres [Termes IGN] modèle de croissance végétale [Termes IGN] semis de points [Termes IGN] volume en bois
Résumé :	(auteur) Full waveform (FW) LiDAR systems have proven their effectiveness to map forest biophysical variables in the last two decades, owing to their ability of measuring, with high accuracy, forest vertical structures. The Global Ecosystem Dynamics Investigation (GEDI) system on board the International Space Station (ISS) is the latest FW spaceborne LiDAR instrument for the continuous observation of Earth's forests. FW systems rely on very sophisticated pre-processing steps to generate a priori metrics in order to leverage their capabilities for the accurate estimation of the aforementioned forest characteristics. The ever-expanding volume of acquired GEDI data, which to date comprises more than 25 billion acquired unfiltered shots, and along with the pre-processed data, amounting to more than 90 TB of data, raises new challenges in terms of adapted preprocessing methods for the suitable exploitation of such a huge and complex amount of LiDAR data. To overcome the issues related to the generation of relevant metrics from GEDI data, we propose a new metric-free approach to estimate canopy dominant heights (Hdom) and wood volume (V) of Eucalyptus plantations over five different regions in Brazil. To avoid metric computation, we leverage deep learning techniques and, more in detail, convolutional neural networks with the aim to analyze the GEDI Level 1B geolocated waveforms. Performance comparisons were conducted between four convolutional neural network (CNN) variants using GEDI waveform data (either untouched, or subsetted) and a metric based Random Forest regressor (RF). Additionally, we tested if our framework can improve the generalization of the models to different distant regions. First, the models were trained using data from all the study regions. Cross validated results showed that the CNN based models compared well against their RF counterpart for both Hdom and V. The RMSE on the estimation of Hdom from the CNN based models varied between 1.54 and 1.94 m with a coefficient of determination (R2) between 0.86 and 0.91, while the RF model produced an accuracy on Hdom estimates of 1.45 m (R2 = 0.92). For V, CNN based estimations ranged from 27.76 to 33.33 m3.ha−1 (R2 between 0.82 and 0.88), while for RF, the RMSE was 27.61 m3.ha−1 (R2 = 0.88). Next, model generalization was assessed by means of a spatial transfer experiment. For Hdom, both the CNN and RF approaches showed similar performances to a global model, however, the CNN based approach showed higher variability on the estimation accuracy, and the variability was related to the forest structure between the trained and tested data (similar tree heights yield better accuracies). For the estimation of V, considering both approaches, the accuracy was dependent on the allometric relationship between Hdom and V in the training and testing regions while lower accuracies on V were obtained when the testing and training regions exhibited a different allometric relationship.
Numéro de notice :	A2021-869
Affiliation des auteurs :	non IGN
Thématique :	FORET/IMAGERIE
Nature :	Article
DOI :	10.1016/j.rse.2021.112652
Date de publication en ligne :	31/08/2021
En ligne :	https://doi.org/10.1016/j.rse.2021.112652
Format de la ressource électronique :	URL article
Permalink :	https://documentation.ensg.eu/index.php?lvl=notice_display&id=99118

vignette

IGN

IGN / ENSG

Centre de documentation
scientifique
6 et 8 Avenue Blaise Pascal
Cité Descartes
Champs-sur-Marne
77455 Marne la Vallée
Cedex 2
L'IGN a pour vocation

de décrire la surface du territoire national et l'occupation de son sol, et d'élaborer et de mettre à jour l'inventaire permanent des ressources forestières nationales.
Accès directs
2014 -2024 IGN