deadtrees.earth-aerial: A Multi-Resolution Aerial Image Dataset for Tree Cover and Mortality Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914580307902464 |
|---|---|
| author | Sharma, Ayushi Mosig, Clemens Drees, Lukas Soltani, Salim Vajna-Jehle, Janusch Sheppard, Aaron Ahmadi, Belqis Schmid, Jonathan Neumeier, Paul Jacobs, Nathan Wegner, Jan Dirk Kattenborn, Teja |
| author_facet | Sharma, Ayushi Mosig, Clemens Drees, Lukas Soltani, Salim Vajna-Jehle, Janusch Sheppard, Aaron Ahmadi, Belqis Schmid, Jonathan Neumeier, Paul Jacobs, Nathan Wegner, Jan Dirk Kattenborn, Teja |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_19605 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | deadtrees.earth-aerial: A Multi-Resolution Aerial Image Dataset for Tree Cover and Mortality Detection Sharma, Ayushi Mosig, Clemens Drees, Lukas Soltani, Salim Vajna-Jehle, Janusch Sheppard, Aaron Ahmadi, Belqis Schmid, Jonathan Neumeier, Paul Jacobs, Nathan Wegner, Jan Dirk Kattenborn, Teja Computer Vision and Pattern Recognition 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. |
| title | deadtrees.earth-aerial: A Multi-Resolution Aerial Image Dataset for Tree Cover and Mortality Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.19605 |