Assessing the impact of LiDAR density and input features on forest canopy height estimation through XGBoost, CNN, and CNN + transformer approaches
Accurate estimation of forest Canopy Height Model (CHM) is essential for understanding ecosystem structure, biomass, and carbon dynamics. Machine learning (ML) and deep learning (DL) models have shown strong potential when trained using LiDAR-derived (Light Detection and Ranging) canopy heights as r...
| Autores: | , , , |
|---|---|
| Tipo de documento: | artigo |
| Data de publicação: | 2026 |
| País: | España |
| Recursos: | Universidad de Cantabria (UC) |
| Repositório: | UCrea Repositorio Abierto de la Universidad de Cantabria |
| Idioma: | inglês |
| OAI Identifier: | oai:repositorio.unican.es:10902/39682 |
| Acesso em linha: | https://hdl.handle.net/10902/39682 |
| Access Level: | Acceso aberto |
| Palavra-chave: | Canopy height model LiDAR Machine learning Deep learning Convolutional neural networks Transformers |
| Resumo: | Accurate estimation of forest Canopy Height Model (CHM) is essential for understanding ecosystem structure, biomass, and carbon dynamics. Machine learning (ML) and deep learning (DL) models have shown strong potential when trained using LiDAR-derived (Light Detection and Ranging) canopy heights as reference data. However, the influence of LiDAR point density on model performance remains poorly understood. This study systematically evaluates three modeling frameworks, Extreme Gradient Boosting (XGBoost), Convolutional Neural Networks (CNN) and hybrid CNN–Transformer architectures, for predicting CHM across multiple regions in Spain, using LiDAR data with varying point densities (1–5 points/m2) from the Plan Nacional de Ortofotografía Aérea (PNOA). Models were trained using multiple sources of remote sensing data: Sentinel-2 spectral bands (visible and near-infrared bands at 10 m) and Sentinel-1 VH backscatter and topographic variables (slope and elevation). Model performance was assessed in terms of predictive accuracy, generalization capacity and sensitivity to LiDAR point density data. Results show that CNN-based approaches outperform classical ML across all datasets, and that integrating Transformer modules further improves performance particularly in areas with higher LiDAR density. The best results were achieved on the dataset with higher point density (5 points/m2), where the CNN + Transformer model reached a Mean Absolute Error (MAE) of 3.37 ± 0.1 m and an R2 of 0.66 ± 0.02. Lower-density LiDAR datasets degraded the accuracy for all methods. These findings highlight that both model architecture and LiDAR point density critically influence CHM estimation. The results provide practical guidance for designing large-scale structural mapping workflows in regions with heterogeneous LiDAR coverage, helping to support forest management, carbon accounting and environmental decision-making. |
|---|