.png){kind=icon}
.png){kind=icon}
Return
A Deep Learning-Based Model for Forest Canopy Height Mapping Using Multisource Remote Sensing Data
.png){kind=icon}
OA
AI
DOI：10.1109/JSTARS.2026.3653676.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Forest canopy height is a critical structural parameter for accurately assessing forest carbon storage. This study integrates Global Ecosystem Dynamics Investigation (GEDI) LiDAR data with multisource remote sensing features to construct a multidimensional feature space comprising 13 parameters. By employing high-dimensional feature vectors of “spatial coordinates + environmental features,” the proposed deep learning-based neural network-guided interpolation (NNGI) model effectively harnesses the capacity of deep learning to model complex nonlinear relationships and adaptively extract local features. This method adopts a dual-network collaborative architecture to dynamically learn interpolation weights based on environmental similarity in the feature space, rather than relying on fixed parameters or merely considering spatial distance, thereby effectively fusing the complex nonlinear relationship modeling capability of deep learning with the concept of spatial interpolation. Experiments conducted across five representative regions in the United States demonstrate that the overall accuracy of the NNGI model significantly outperforms traditional machine learning methods, Pearson correlation coefffcient (r) = 0.79, root-mean-square error (RMSE) = 5.38 m, mean absolute error = 4.04 m, bias = –0.15 m. In areas with low (0% –20% ) and high (61% –80% ) vegetation cover fractions, the RMSE decreased by 37.52% and 5.37%, respectively, while the r-value increased by 15.87% and 35.90%, respectively. Regarding different slope aspects, the RMSE for southeastern and western slopes decreased by 30.38% and 18.70%, respectively. This study provides a more reliable solution for the accurate estimation of forest structural parameters in complex environments.
Keywords:
Deep learning model
forest canopy height
Global Ecosystem Dynamics Investigation (GEDI)
multisource remote sensing
neural network-guided interpolation (NNGI)
Journal
IF:
5.3
Papers:
1.3K
Citations:
3.0W