Super-resolved canopy height mapping from Sentinel-2 time series using airborne LiDAR HD reference data across metropolitan France
Abstract
Fine-scale forest monitoring is essential for understanding canopy structure and its dynamics, which are key indicators of carbon stocks, biodiversity, and forest health. Deep learning is particularly effective for this task, as it integrates spectral, temporal, and spatial signals that jointly reflect the canopy structure. To address this need, we introduce THREASURE-Net, a novel end-to-end framework for Tree Height REgression And SUper-REsolution. The model is trained on Sentinel-2 time series using reference height metrics derived from LiDAR~HD data at multiple spatial resolutions over Metropolitan France to produce annual height maps. We evaluate three model variants, producing tree-height predictions at 2.5 m, 5 m, and 10 m resolution. THREASURE-Net does not rely on any pretrained model, nor on reference very high resolution optical imagery to train its super-resolution module; instead, it learns solely from LiDAR-derived height information. Our approach outperforms existing state-of-the-art methods based on Sentinel data and is competitive with methods based on very high resolution imagery. It can be deployed to generate high-precision annual canopy-height maps, achieving mean absolute errors of 2.63 m, 2.70 m, and 2.89 m at 10 m, 5 m, and 2.5 m resolution, respectively. These results highlight the potential of THREASURE-Net for scalable and cost-effective structural monitoring of temperate forests using only freely available satellite data. The source code for THREASURE-Net is available at: https://github.com/Global-Earth-Observation/threasure-net
Related
- Threshold Sensitivity and Reference Uncertainty in Sentinel-1 Inundation Mapping: The July 2021 Mahad Flood
- Separation of Source, Site, and Path Effects Based on Elastic Radiative Transfer Theory. Part 1: Mapping of Scattering and Absorption Properties and Application to Metropolitan France
- Mapping Land Use Typologies During Fallow Periods in France Using Sentinel-1 and -2 Time-Series
- Evaluating Cross-Country Generalization of Deep Learning-Based Flood Mapping Using Sentinel-1 SAR and Sentinel-2 Imagery
- Mapping landslide change and volume with repeat airborne LiDAR after the May 2023 Emilia-Romagna event: slope-dependent detection limits and lowered areas
BibTeX
@article{kalinicheva2026superresolved,
title = {{Super-resolved canopy height mapping from Sentinel-2 time series using airborne LiDAR HD reference data across metropolitan France}},
author = {Ekaterina Kalinicheva and Florian Helen and Stéphane Mermoz and Florian Mouret and Milena Planells},
journal = {Remote Sensing of Environment},
year = {2026},
month = jun,
doi = {10.1016/j.rse.2026.115536},
eprint = {2512.11524},
archivePrefix = {arXiv},
url = {https://ut-toulouseinp.hal.science/hal-05795167v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Super-resolved canopy height mapping from Sentinel-2 time series using airborne LiDAR HD reference data across metropolitan France
AU - Ekaterina Kalinicheva
AU - Florian Helen
AU - Stéphane Mermoz
AU - Florian Mouret
AU - Milena Planells
PY - 2026
DA - 2026/06/24
JO - Remote Sensing of Environment
DO - 10.1016/j.rse.2026.115536
UR - https://ut-toulouseinp.hal.science/hal-05795167v1
AB - Fine-scale forest monitoring is essential for understanding canopy structure and its dynamics, which are key indicators of carbon stocks, biodiversity, and forest health. Deep learning is particularly effective for this task, as it integrates spectral, temporal, and spatial signals that jointly reflect the canopy structure. To address this need, we introduce THREASURE-Net, a novel end-to-end framework for Tree Height REgression And SUper-REsolution. The model is trained on Sentinel-2 time series using reference height metrics derived from LiDAR~HD data at multiple spatial resolutions over Metropolitan France to produce annual height maps. We evaluate three model variants, producing tree-height predictions at 2.5 m, 5 m, and 10 m resolution. THREASURE-Net does not rely on any pretrained model, nor on reference very high resolution optical imagery to train its super-resolution module; instead, it learns solely from LiDAR-derived height information. Our approach outperforms existing state-of-the-art methods based on Sentinel data and is competitive with methods based on very high resolution imagery. It can be deployed to generate high-precision annual canopy-height maps, achieving mean absolute errors of 2.63 m, 2.70 m, and 2.89 m at 10 m, 5 m, and 2.5 m resolution, respectively. These results highlight the potential of THREASURE-Net for scalable and cost-effective structural monitoring of temperate forests using only freely available satellite data. The source code for THREASURE-Net is available at: https://github.com/Global-Earth-Observation/threasure-net
SN - 0034-4257
SN - 1879-0704
ER -