Preprints
https://doi.org/10.5194/gmd-2024-95
https://doi.org/10.5194/gmd-2024-95
Submitted as: methods for assessment of models
 | 
05 Jun 2024
Submitted as: methods for assessment of models |  | 05 Jun 2024
Status: this preprint is currently under review for the journal GMD.

Remote sensing-based high-resolution mapping of the forest canopy height: some models are useful, but might they be even more if combined?

Nikola Besic, Nicolas Picard, Cédric Vega, Lionel Hertzog, Jean-Pierre Renaud, Fajwel Fogel, Agnès Pellissier-Tanon, Gabriel Destouet, Milena Planells-Rodriguez, and Philippe Ciais

Abstract. 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 an extensive availability of multiple sources of information, which can either lead to a potential confusion, or to the possibility to learn both about models and about forest attributes through the joint interpretation of multiple models. This article seeks to endorse the latter, by relying on the Bayesian model averaging (BMA) approach, which can be used to diagnose and interpret differences among predictions of different models. The predictions in our case are the forest canopy height estimations for the metropolitan France coming from five different models (Lang et al., 2023; Liu et al., 2023; Morin et al., 2022; Potapov et al., 2021; Schwartz et al., 2024). An independent reference dataset, containing four different definitions of the forest height (dominant, mean, maximum and Lorey’s), comes from the French National Forest Inventory (NFI) providing some 5 500 plots used in the study, distributed across the entire area of interest. In this contribution, we line up the evoked models with respect to their probabilities to be the ones generating measurements/estimations at the NFI plots. Stratifying the probabilities based on French sylvo-ecological regions reveals spatial variation in the respective model probabilities across the area of interest. Furthermore, we observe significant variability in these probabilities depending on the forest height definition used. This leads us to infer that the different models inadvertently exhibit dominant predictions for different types of canopy height. We also present the respective inter-model and intra-model variance estimations, allowing us to come to understand where the employed models have comparable weights but contrasted predictions. We show that the mountainous terrain has an important impact on the models spread. Moreover, we observe that the forest stand vertical structure, the dominant tree species and the type of forest ownership systematically appear to be statistically significant factors influencing the models divergence. Finally, we demonstrate that the derived mixture models exhibit higher R2 scores and lower RMSE values compared to individual models, although they may not necessarily exhibit lower biases.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Nikola Besic, Nicolas Picard, Cédric Vega, Lionel Hertzog, Jean-Pierre Renaud, Fajwel Fogel, Agnès Pellissier-Tanon, Gabriel Destouet, Milena Planells-Rodriguez, and Philippe Ciais

Status: open (until 31 Jul 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Nikola Besic, Nicolas Picard, Cédric Vega, Lionel Hertzog, Jean-Pierre Renaud, Fajwel Fogel, Agnès Pellissier-Tanon, Gabriel Destouet, Milena Planells-Rodriguez, and Philippe Ciais
Nikola Besic, Nicolas Picard, Cédric Vega, Lionel Hertzog, Jean-Pierre Renaud, Fajwel Fogel, Agnès Pellissier-Tanon, Gabriel Destouet, Milena Planells-Rodriguez, and Philippe Ciais

Viewed

Total article views: 161 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
118 33 10 161 4 5
  • HTML: 118
  • PDF: 33
  • XML: 10
  • Total: 161
  • BibTeX: 4
  • EndNote: 5
Views and downloads (calculated since 05 Jun 2024)
Cumulative views and downloads (calculated since 05 Jun 2024)

Viewed (geographical distribution)

Total article views: 158 (including HTML, PDF, and XML) Thereof 158 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 12 Jun 2024
Download
Short summary
The creation of advanced mapping models for forest attributes, utilizing remote sensing data and incorporating machine or deep learning methods, has become a key area of interest in the domain of forest observation and monitoring. This paper introduces a method where we blend and collectively interpret five models dedicated to estimating forest canopy height. We achieve this through Bayesian model averaging, offering a comprehensive approach to height estimation in forest ecosystems.