A CNN-based approach for the estimation of canopy heights and wood volume from GEDI waveforms

Autor: Fayad, Ibrahim, Ienco, Dino, Baghdadi, Nicolas, Gaetano, Raffaele, Alvares, Clayton, Stape, Jose, Ferraço Scolforo, Henrique, Le Maire, Guerric
Přispěvatelé: AgroParisTech, Universidade Estadual Paulista (UNESP), Estrada Limeira, UMR Eco&Sols, Montpellier SupAgro, Territoires, Environnement, Télédétection et Information Spatiale (UMR TETIS), Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad)-AgroParisTech-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Département Environnements et Sociétés (Cirad-ES), Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad), Universidade Estadual Paulista Júlio de Mesquita Filho = São Paulo State University (UNESP), Ecologie fonctionnelle et biogéochimie des sols et des agro-écosystèmes (UMR Eco&Sols), Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad)-Institut de Recherche pour le Développement (IRD)-Centre international d'études supérieures en sciences agronomiques (Montpellier SupAgro)-Institut national d’études supérieures agronomiques de Montpellier (Montpellier SupAgro), Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro)-Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Département Performances des systèmes de production et de transformation tropicaux (Cirad-PERSYST), French Space Study Center (CNES), National Research Institute for Agriculture, Food and the Environment (INRAE), Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad)-Institut de Recherche pour le Développement (IRD)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Institut Agro - Montpellier SupAgro, Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro)-Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro)
Jazyk: angličtina
Rok vydání: 2021
Předmět:
Zdroj: Remote Sensing of Environment
Scopus
Repositório Institucional da UNESP
Universidade Estadual Paulista (UNESP)
instacron:UNESP
Remote Sensing of Environment, Elsevier, 2021, 265, pp.112652. ⟨10.1016/j.rse.2021.112652⟩
Remote Sensing of Environment, 2021, 265, 16 p. ⟨10.1016/j.rse.2021.112652⟩
ISSN: 0034-4257
1879-0704
DOI: 10.1016/j.rse.2021.112652⟩
Popis: Made available in DSpace on 2022-04-28T19:44:02Z (GMT). No. of bitstreams: 0 Previous issue date: 2021-11-01 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. French National Research Institute for Agriculture Food and the Environment (INRAE) CIRAD CNRS TETIS Univ Montpellier AgroParisTech, 34093 Montpellier CEDEX 5 Unesp Faculdade de Ciências Agronômicas Suzano SA Estrada Limeira, 391, 13465-970 CIRAD UMR Eco&Sols Eco&Sols Univ Montpellier CIRAD INRAE IRD Montpellier SupAgro Unesp Faculdade de Ciências Agronômicas
Databáze: OpenAIRE
Externí odkaz: