Remote-sensing-based forest canopy height mapping: Some models are useful, but might they provide us with even more insights when combined?

Besic Nikola, Picard Nicolas, Vega Cédric, Bontemps Jean-Daniel, Hertzog Lionel, Renaud Jean-Pierre, Fogel Fajwel, Schwartz Martin, Pellissier-Tanon Agnès, Destouet Gabriel, Mortier Frédéric, Planells-Rodriguez Milena, Ciais Philippe. 2025. Remote-sensing-based forest canopy height mapping: Some models are useful, but might they provide us with even more insights when combined?. GeoScientific Model Development, 18 (2) : 337-359.

Résumé : The development of high-resolution mapping models for forest attributes based on remote sensing data combined with machine or deep learning techniques has become a prominent topic in the field of forest observation and monitoring. This has resulted in the availability of multiple, sometimes conflicting, sources of information, but, at face value, it also makes it possible to learn about forest attribute uncertainty through the joint interpretation of multiple models. This article seeks to endorse the latter by utilizing the Bayesian model averaging approach to diagnose and interpret the differences between predictions from different models. The predictions in our case are forest canopy height estimations for metropolitan France arising from five different models. An independent reference dataset, containing four different definitions of forest height (dominant, mean, maximum, and Lorey's) was established based on around 5500 plots of the French National Forest Inventory (NFI), distributed across the entire area of interest. In this study, we evaluate models with respect to their probabilities of correctly predicting measurements or estimations obtained from NFI plots, highlighting the spatial variability in respective model probabilities across the study area. We observed significant variability in these probabilities depending on the forest height definition used, implying that the different models inadvertently predict different types of canopy height. We also present the respective inter-model and intra-model variance estimations, enabling us to grasp where the employed models have comparable contributions but contrasting predictions. We show that topography has an important impact on the models spread. Moreover, we observed that the forest stand vertical structure, the dominant tree species, and the type of forest ownership systematically emerge as statistically significant factors influencing the model divergences. Finally, we observed that the fitted higher-order mixtures, which enabled the presented analyses, do not necessarily reduce bias or prevent the saturation of the predicted heights observed in the individual models.

Mots-clés Agrovoc : télédétection, modèle mathématique, forêt, forêt tropicale, cartographie, inventaire forestier, hauteur, mesure (activité), aménagement forestier, structure du peuplement, couvert, radar, dendrométrie, biomasse

Mots-clés géographiques Agrovoc : France

Agences de financement hors UE : Centre National d'Etudes Spatiales, Agence Nationale de la Recherche

Projets sur financement : (FRA) SLIM, (FRA) SylvoSanSat, (FRA) Recherches avancées sur l'arbre et les écosytèmes forestiers, (FRA) Intelligence Artificielle pour la surveillance des forêts depuis l'espace

Auteurs et affiliations

• Besic Nikola, IGN [Institut géographique national] (FRA) - auteur correspondant
• Picard Nicolas, GIP ECOFOR (FRA)
• Vega Cédric, IGN [Institut géographique national] (FRA)
• Bontemps Jean-Daniel, IGN [Institut géographique national] (FRA)
• Hertzog Lionel, IGN [Institut géographique national] (FRA)
• Renaud Jean-Pierre, ONF (FRA)
• Fogel Fajwel, ENS (FRA)
• Schwartz Martin, Université Paris-Saclay (FRA)
• Pellissier-Tanon Agnès, Université Paris-Saclay (FRA)
• Destouet Gabriel, INRAE (FRA)
• Mortier Frédéric, CIRAD-BIOS-UMR AMAP (FRA)
• Planells-Rodriguez Milena, CNES (FRA)
• Ciais Philippe, CNRS (FRA)

Source : Cirad-Agritrop (https://agritrop.cirad.fr/614080/)

Métriques

[ Page générée et mise en cache le 2025-09-09 ]