Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Mapping forest tree species and their uncertainty using Earth observation and National Forest Inventory data : towards operational monitoring in Sweden

Abdi, Abdulhakim M. LU orcid and Wang, Fan LU (2026) In International Journal of Remote Sensing 47(7). p.2912-2943
Abstract

Timely, detailed information on forest composition is essential for effective management, biodiversity protection, and understanding ecosystem dynamics. This study maps the distribution of seven dominant tree species in Swedish forests and produces spatially explicit, pixel-level estimates of classification uncertainty. The mapping framework integrates multitemporal Sentinel-1 radar and Sentinel-2 optical observations with field data from the Swedish National Forest Inventory and auxiliary predictors describing topography and canopy height. We trained a Bayesian-optimized extreme gradient boosting model on spatiotemporal metrics derived from these datasets and quantified classification confidence through entropy computed from the... (More)

Timely, detailed information on forest composition is essential for effective management, biodiversity protection, and understanding ecosystem dynamics. This study maps the distribution of seven dominant tree species in Swedish forests and produces spatially explicit, pixel-level estimates of classification uncertainty. The mapping framework integrates multitemporal Sentinel-1 radar and Sentinel-2 optical observations with field data from the Swedish National Forest Inventory and auxiliary predictors describing topography and canopy height. We trained a Bayesian-optimized extreme gradient boosting model on spatiotemporal metrics derived from these datasets and quantified classification confidence through entropy computed from the class-probability outputs. We applied a spatial block partitioning approach to limit the effects of spatial autocorrelation between optimization and validation data and ensure a more realistic assessment of the model’s generalization capacity. Model overall accuracy reached 85% (F1 = 0.82) using a 60 m spatial block validation. Under a more conservative 200 m block configuration, performance decreased to F1 = 0.63, reflecting reduced training data availability. The county-level species coverage derived from the classification aligned closely with published figures from the Swedish Forest Agency (Spearman’s ρ = 0.94, 95% CI: 0.89–0.96, p < 0.001). Variable importance analysis showed that Sentinel-2 spectral bands, particularly shortwave-infrared and red-edge captured during spring and summer, contributed most to species discrimination, while Sentinel-1 backscatter provided complementary structural information. The integration of forest inventory data, Earth observation, and machine learning to produce tree species maps and a spatially explicit measure of prediction uncertainty yields a robust and reproducible framework for large-area forest mapping. The results provide detailed, spatially continuous information on species composition along with an accompanying confidence surface. This offers practical value for ecological assessments, regional planning, and emerging legislative and environmental goals. The data are freely available for download and the maps can be interactively visualized using this link: https://ee-treespec.projects.earthengine.app/view/treespec.

(Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
forest monitoring, National Forest Inventory, remote sensing, Sentinel-1, Sentinel-2, tree species mapping
in
International Journal of Remote Sensing
volume
47
issue
7
pages
2912 - 2943
publisher
Taylor & Francis
external identifiers
  • scopus:105029876664
ISSN
0143-1161
DOI
10.1080/01431161.2026.2625513
language
English
LU publication?
yes
id
056535ee-55f5-4da9-8dff-12b8e732595a
date added to LUP
2026-02-27 13:16:42
date last changed
2026-06-10 09:11:13
@article{056535ee-55f5-4da9-8dff-12b8e732595a,
  abstract     = {{<p>Timely, detailed information on forest composition is essential for effective management, biodiversity protection, and understanding ecosystem dynamics. This study maps the distribution of seven dominant tree species in Swedish forests and produces spatially explicit, pixel-level estimates of classification uncertainty. The mapping framework integrates multitemporal Sentinel-1 radar and Sentinel-2 optical observations with field data from the Swedish National Forest Inventory and auxiliary predictors describing topography and canopy height. We trained a Bayesian-optimized extreme gradient boosting model on spatiotemporal metrics derived from these datasets and quantified classification confidence through entropy computed from the class-probability outputs. We applied a spatial block partitioning approach to limit the effects of spatial autocorrelation between optimization and validation data and ensure a more realistic assessment of the model’s generalization capacity. Model overall accuracy reached 85% (F1 = 0.82) using a 60 m spatial block validation. Under a more conservative 200 m block configuration, performance decreased to F1 = 0.63, reflecting reduced training data availability. The county-level species coverage derived from the classification aligned closely with published figures from the Swedish Forest Agency (Spearman’s ρ = 0.94, 95% CI: 0.89–0.96, p &lt; 0.001). Variable importance analysis showed that Sentinel-2 spectral bands, particularly shortwave-infrared and red-edge captured during spring and summer, contributed most to species discrimination, while Sentinel-1 backscatter provided complementary structural information. The integration of forest inventory data, Earth observation, and machine learning to produce tree species maps and a spatially explicit measure of prediction uncertainty yields a robust and reproducible framework for large-area forest mapping. The results provide detailed, spatially continuous information on species composition along with an accompanying confidence surface. This offers practical value for ecological assessments, regional planning, and emerging legislative and environmental goals. The data are freely available for download and the maps can be interactively visualized using this link: https://ee-treespec.projects.earthengine.app/view/treespec.</p>}},
  author       = {{Abdi, Abdulhakim M. and Wang, Fan}},
  issn         = {{0143-1161}},
  keywords     = {{forest monitoring; National Forest Inventory; remote sensing; Sentinel-1; Sentinel-2; tree species mapping}},
  language     = {{eng}},
  number       = {{7}},
  pages        = {{2912--2943}},
  publisher    = {{Taylor & Francis}},
  series       = {{International Journal of Remote Sensing}},
  title        = {{Mapping forest tree species and their uncertainty using Earth observation and National Forest Inventory data : towards operational monitoring in Sweden}},
  url          = {{http://dx.doi.org/10.1080/01431161.2026.2625513}},
  doi          = {{10.1080/01431161.2026.2625513}},
  volume       = {{47}},
  year         = {{2026}},
}