deadtrees.earth-aerial: A Multi-Resolution Aerial Image Dataset for Tree Cover and Mortality Detection

2026-05-19

AI Summary

This study addresses the urgent need for scalable joint segmentation methods for canopy cover and tree mortality in global forest monitoring, hindered by the absence of globally representative, multi-resolution aerial imagery datasets. We present the first centimeter-scale (2.5–20 cm) aerial image dataset curated at a global scale, encompassing diverse biomes and forest structures, accompanied by expert-validated high-quality manual annotations and pseudolabels, along with a geographically balanced benchmark suite. Leveraging this dataset, we establish a strong deep learning baseline model that generalizes across biomes and significantly improves performance universally—most notably increasing the F1 score in boreal forests from 0.40 to 0.58 (a 45% relative improvement). The dataset, models, and code will be publicly released.

Abstract

Forests worldwide are increasingly threatened by climate change and disturbances such as fire, pests, and pathogens, creating an urgent need for scalable monitoring of tree cover and tree mortality. Aerial imagery from drones and aircraft is a key data source for detailed and large-scale mapping of tree crowns and mortality. However, related progress is limited by the lack of globally representative, harmonized datasets for joint segmentation of tree cover and mortality. We introduce two novel, open, machine-learning-ready datasets to enable joint segmentation of tree cover and tree mortality from centimeter-scale aerial imagery for the first time at global scales. With DTE-aerial-train, we provide a training dataset comprising 385K image patches of size 1024x1024 pixels, with resolutions ranging from 2.5 to 20 cm. It includes multi-class expert-annotated and -audited pseudo-labels for tree cover and mortality. With DTE-aerial-bench, we provide a geographically balanced benchmark test set of 25 globally distributed orthoimages totaling 525 patches with high-quality expert annotations for both tree cover and mortality. Both the training and benchmark datasets span tropical, temperate, boreal, and dryland biomes and cover a wide range of forest structures and mortality patterns. Using the benchmark test set for evaluation, we establish strong reference baselines that improve mortality segmentation across all biomes and scales with significant gains in challenging regions, such as boreal forests, where the F1 score increases from 0.40 to 0.58 with around 45% relative improvement. All data, models, and code will be publicly released under permissive open-source licenses. An interactive visualization of the benchmark dataset is available at deadtrees.earth/releases/dte-aerial-bench.

Problem

• tree mortality
• tree cover
• aerial imagery
• dataset
• forest monitoring

Innovation

• tree mortality detection
• multi-resolution aerial imagery
• global-scale dataset
• joint segmentation
• forest monitoring