Tree species composition, classification uncertainty, and diversity metrics for Swedish forests based on National Forest Inventory data and satellite remote sensing

This repository contains the data and documentation for the data paper: "Tree species composition, classification uncertainty, and diversity metrics for Swedish forests based on National Forest Inventory data and satellite remote sensing” by Abdulhakim M. Abdi and Fan Wang. The paper is currently under preparation for submission. All the data layers are visualized in a webmap: http://www.treespecies.se/ The repository contains tree species classification raster, a pixel-level entropy raster representing classification uncertainty, uncertainty-weighted tree species fractions, and a suite of forest- and uncertainty-weighted diversity metrics. Together, these resources enable large-area analyses of forest composition, uncertainty propagation, ecological monitoring, biodiversity assessments, sustainable forest management, and the spatial characterization of forest stands across Götaland. Contents Tree_Species_Classification.tif — Discrete raster (8-bit unsigned integer) of dominant tree species predicted by an XGBoost model trained on Sentinel-1/2 and topographic data. The raster values correspond to 1-Norway spruce, 2-Scots pine, 3-Birch, 4-Beech, 5-Oak, 6-Alder, 7-Aspen, 8-Larch, 9-Other species. The file is accompanied by the file Tree_Species_Classification.clr, which is a custom color map that defines the legend in QGIS. Classification_Uncertainty.tif — Continuous raster (16-bit unsigned integer) containing per-pixel Shannon entropy values (0–Hmax), quantifying classification uncertainty. Species_Fractions_100m.zip — Continuous rasters (Float32, 0-100%) representing forest- and entropy-weighted fractional cover of each tree species computed within a moving Gaussian window. Each file corresponds to one of the nine classes (Norway spruce, Scots pine, Birch, Beech, Oak, Alder, Aspen, Larch, and Other species) at a spatial resolution of 1 hectare (100m x 100m). Diversity_Metrics_100m.zip — Continuous rasters (Float32) representing local diversity metrics at a spatial resolution of 1 hectare (100m x 100m). Each file corresponds to one of the six diversity metrics classes (Pielou's Evenness, Gini-Simpson, Shannon's Diversity, Shannon-Hill, Simpson's D, and Species Richness). Spatial characteristics Property Specification Geographic coverage Landsdel Götaland (Skåne, Blekinge, Halland, Kronoberg, Jönköping, Kalmar, Västra Götaland, Östergötland, Gotland counties) Extent 267320, 6133440 : 757330, 6571770 (EPSG:3006 – SWEREF99 TM) Projection Projected (UTM), units in meters Spatial resolution 10 × 10 m (Classification and Uncertainty) | 100 x 100 m (Species Fractions and Diversity Metrics) Raster dimensions 49,001 × 48,833 pixels Origin 267320, 6571770