Skip to main content

ORIGINAL RESEARCH article

Front. Remote Sens.
Sec. Data Fusion and Assimilation
Volume 5 - 2024 | doi: 10.3389/frsen.2024.1484900
This article is part of the Research Topic One Forest Vision Initiative (OFVi) for Monitoring Tropical Forests: The Remote Sensing Pilar View all articles

Canopy Height Mapping in French Guiana Using Multi-Source Satellite Data and Environmental Information in a U-Net Architecture

Provisionally accepted
Kamel Lahssini Kamel Lahssini 1*Nicolas Baghdadi Nicolas Baghdadi 1Guerric Le Maire Guerric Le Maire 2Ibrahim Fayad Ibrahim Fayad 3Ludovic Villard Ludovic Villard 4
  • 1 UMR9000 Territoires, Environnement, Télédétection et Information Spatiale (TETIS), Montpellier, Languedoc-Roussillon, France
  • 2 IRD UMR210 Ecologie fonctionnelle et biogéochimie des sols et des agro-écosystèmes (Eco&Sols), Montpellier, Languedoc-Roussillon, France
  • 3 Institut Pierre Simon Laplace (IPSL), Paris, Île-de-France, France
  • 4 UMR5126 Centre d'études spatiales de la biosphère (CESBIO), Toulouse, Midi-Pyrénées, France

The final, formatted version of the article will be published soon.

    Canopy height is a key indicator of tropical forest structure. In this study, we present a deep learning application to map canopy height in French Guiana using freely available multi-source satellite data (optical and radar) and complementary environmental information. The potential of a U-Net architecture trained on sparse and unevenly distributed GEDI data to generate a continuous canopy height map at a regional scale was assessed. The developed model, named CHNET, successfully produced a canopy height map of French Guiana at a 10-m spatial resolution, achieving relatively good accuracy compared to a validation airborne LiDAR scanning (ALS) dataset. The study demonstrates that relevant environmental descriptors, namely height above nearest drainage (HAND) and forest landscape types (FLT), significantly contribute to the model's accuracy, highlighting that these descriptors bring important information on canopy structural properties and that the CHNET framework can efficiently use this information to improve canopy height prediction. Another critical aspect highlighted is the necessity of addressing GEDI data inaccuracies and geolocation uncertainties, which is essential for any GEDI-based application. However, challenges remain, particularly in characterizing tall canopies, as our CHNET model exhibits a tendency to underestimate canopy heights greater than 35 m. A large part of this error arises from the use of GEDI measurements as reference, given the fact these data exhibit certain saturation in tropical biomes. Future improvements in the analysis of GEDI signal as well as the implementation of robust models are essential for better characterization of dense and tall tropical forest ecosystems.

    Keywords: Canopy height, DATA FUSION, deep learning, French Guiana, GEDI, lidar, tropical forests

    Received: 22 Aug 2024; Accepted: 31 Oct 2024.

    Copyright: © 2024 Lahssini, Baghdadi, Le Maire, Fayad and Villard. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Kamel Lahssini, UMR9000 Territoires, Environnement, Télédétection et Information Spatiale (TETIS), Montpellier, 34093, Languedoc-Roussillon, France

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.