Sub-meter tree height mapping of California using aerial images and LiDAR-informed U-Net model
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Sub-meter tree height mapping of California using aerial images and LiDAR-informed U-Net model. / Wagner, Fabien H.; Roberts, Sophia; Ritz, Alison L.; Carter, Griffin; Dalagnol, Ricardo; Favrichon, Samuel; Hirye, Mayumi C.M.; Brandt, Martin; Ciais, Philippe; Saatchi, Sassan.
I: Remote Sensing of Environment, Bind 305, 114099, 2024.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Sub-meter tree height mapping of California using aerial images and LiDAR-informed U-Net model
AU - Wagner, Fabien H.
AU - Roberts, Sophia
AU - Ritz, Alison L.
AU - Carter, Griffin
AU - Dalagnol, Ricardo
AU - Favrichon, Samuel
AU - Hirye, Mayumi C.M.
AU - Brandt, Martin
AU - Ciais, Philippe
AU - Saatchi, Sassan
N1 - Publisher Copyright: © 2024 The Authors
PY - 2024
Y1 - 2024
N2 - Tree canopy height is one of the most important indicators of forest biomass, productivity, and ecosystem structure, but it is challenging to measure accurately from the ground and from space. Here, we used a U-Net model adapted for regression to map the canopy height of all trees in the state of California with very high-resolution aerial imagery 0.6 m from the USDA-NAIP program. The U-Net model was trained using canopy height models computed from aerial LiDAR data as a reference, along with corresponding RGB-NIR NAIP images collected in 2020. We evaluated the performance of the deep-learning model using 42 independent 1 km2 areas across various forest types and landscape variations in California. Our predictions of tree heights exhibited a mean error of 2.9 m and showed relatively low systematic bias across the entire range of tree heights present in California. In 2020, trees taller than 5 m covered ∼ 19.3% of California. Our model successfully estimated canopy heights up to 50 m without saturation, outperforming existing canopy height products from global models. The approach we used allowed for the reconstruction of the three-dimensional structure of individual trees as observed from nadir-looking optical airborne imagery, suggesting a relatively robust estimation and mapping capability, even in the presence of image distortion. These findings demonstrate the potential of large-scale mapping and monitoring of tree height, as well as potential biomass estimation, using NAIP imagery.
AB - Tree canopy height is one of the most important indicators of forest biomass, productivity, and ecosystem structure, but it is challenging to measure accurately from the ground and from space. Here, we used a U-Net model adapted for regression to map the canopy height of all trees in the state of California with very high-resolution aerial imagery 0.6 m from the USDA-NAIP program. The U-Net model was trained using canopy height models computed from aerial LiDAR data as a reference, along with corresponding RGB-NIR NAIP images collected in 2020. We evaluated the performance of the deep-learning model using 42 independent 1 km2 areas across various forest types and landscape variations in California. Our predictions of tree heights exhibited a mean error of 2.9 m and showed relatively low systematic bias across the entire range of tree heights present in California. In 2020, trees taller than 5 m covered ∼ 19.3% of California. Our model successfully estimated canopy heights up to 50 m without saturation, outperforming existing canopy height products from global models. The approach we used allowed for the reconstruction of the three-dimensional structure of individual trees as observed from nadir-looking optical airborne imagery, suggesting a relatively robust estimation and mapping capability, even in the presence of image distortion. These findings demonstrate the potential of large-scale mapping and monitoring of tree height, as well as potential biomass estimation, using NAIP imagery.
KW - Canopy height models
KW - Deep learning regression
KW - Land-cover
KW - TensorFlow 2
KW - U-Net
KW - Very high-resolution images
U2 - 10.1016/j.rse.2024.114099
DO - 10.1016/j.rse.2024.114099
M3 - Journal article
AN - SCOPUS:85188828221
VL - 305
JO - Remote Sensing of Environment
JF - Remote Sensing of Environment
SN - 0034-4257
M1 - 114099
ER -
ID: 390179402