デンマーク全国樹種マップ

Unofficial AI-generated summary based on the public title and abstract. Not an official translation.

🔬研究者:Provides a reproducible method for national tree species mapping using ML and satellite data, useful for carbon sink estimation.

🏢実務担当者:Can be used for forest carbon accounting and sustainability reporting, though non-commercial license limits direct business use.

🏛政策担当者:Demonstrates a data-driven approach for monitoring forest composition, relevant for national climate and biodiversity reporting.

This dataset provides wall-to-wall predictions of tree species composition across Denmark at 10 m spatial resolution. The maps were generated using machine learning models trained on Danish National Forest Inventory (NFI) observations and satellite-based remote sensing data, including Sentinel-1, Sentinel-2, and canopy height information.   Files `tree_species_map_forest.tif` `tree_species_map_DHI.tif` `tree_species_map_full.tif` Description All files are single-band categorical rasters with the predicted tree type codes (0–8), corresponding to the table below. tree_species_map_forest.tif This file contains predictions only in areas covered by the  Danish Digital Forest Map . tree_species_map_DHI.tif This file contains predictions only in areas that are classified as trees using the  DHI tree cover map dataset . tree_species_map_full.tif This file contains predictions all accross Denmark without any filtering.  Tree type codes Code English     Danish     0 Other Broadleaf (OBL) Andet løv (ANL) 1 Fir Ædelgran 2 Beech Bøg 3 Birch Birk 4 Larch Lærk 5 Maple Ahorn 6 Oak Eg 7 Pine Fyr 8 Spruce Gran   Methodology For both the tree cover and tree type classification, we used a combination of Sentinel-1, Sentinel-2, and canopy height data. Specifically:\ Sentinel-1 Sentinel-1 dual-polarisation VV and VH backscatter coefficients were used as multi-temporal time series from 2020 to 2022, as well as the difference between VH and VV. Sentinel-2 Multi-temporal Sentinel-2 data were used from 2020 to 2022 from all bands except bands 1, 9, and 10.  In addition to the spectral bands, we computed a list of spectral indices. Canopy height Canopy height information was derived from national elevation data provided by the Danish Agency for Data Supply and Infrastructure (Dataforsyningen). The dataset includes a digital terrain model (DTM) and a digital surface model (DSM) with a spatial resolution of 0.4 m. Classification   For the classification experiments, we used training data from the Danish NFI, provided from the University of Copenhagen (KU), and trained a multi-layer perceptron (MLP)  Part of this work is based on a research grand from INNO-CCUS, the Danish government’s CCUS (carbon capture, utilisation and storage) research partnership, supported by Innovation Fond Denmark. Governance around use of the dataset refers to Creative Commons BY-NC-ND 4.0 ( Deed - Attribution-NonCommercial-NoDerivatives 4.0 International - Creative Commons ), which allows reusers to copy and distribute the material in any medium or format in unadapted form and for noncommercial purposes only. Credit must be given to DHI. Only noncommercial use of dataset is permitted. Noncommercial means not primarily intended for or directed towards commercial advantage or monetary compensation. No derivatives or adaptations of the dataset is permitted.  For access to the full probablities of the model or any other questions you can contact Lotte Nyborg, [email protected] or Alkiviadis Koukos, [email protected].

• Zenodo https://zenodo.org/records/22108850first seen 2026-08-27 04:33:35 · last seen 2026-08-30 04:12:41