Tree mortality has escalated worldwide in recent years due to climate warming and unprecedented drought events. However, mapping tree mortality across forest ecosystems has not yet been achieved. Aerial photos provide opportunities to reveal the spatial and spectral characteristics of canopy death at local to landscape scales. In this work, we present a deep learning model for mapping tree mortality from aerial photos in various forested ecosystems across Europe. This model builds on a baseline model trained with data on dead tree canopies from California using sub-meter resolution aerial photos and allows the use of various spatial resolutions of the input images (ranging from 10 to 60 cm). By comparing our results to ground observations and/or state-of-the-art forest disturbance and loss products, we will discuss the advantages and limitations of aerial photo-based tree mortality mapping. The proposed …
%0 Journal Article
%1 cheng2024highresolution
%A Cheng, Yan
%A Oehmcke, Stefan
%A Mosig, Clemens
%A Mirela, Beloiu
%A Kattenborn, Teja
%A Abel, Christin
%A Gominski, Dimitri
%A Nord-Larsen, Thomas
%A Fensholt, Rasmus
%A Horion, Stephanie
%D 2024
%I Copernicus Meetings
%K imported topic_earthenvironment
%N EGU24-20213
%T High-resolution mapping of tree mortality in European forests
%X Tree mortality has escalated worldwide in recent years due to climate warming and unprecedented drought events. However, mapping tree mortality across forest ecosystems has not yet been achieved. Aerial photos provide opportunities to reveal the spatial and spectral characteristics of canopy death at local to landscape scales. In this work, we present a deep learning model for mapping tree mortality from aerial photos in various forested ecosystems across Europe. This model builds on a baseline model trained with data on dead tree canopies from California using sub-meter resolution aerial photos and allows the use of various spatial resolutions of the input images (ranging from 10 to 60 cm). By comparing our results to ground observations and/or state-of-the-art forest disturbance and loss products, we will discuss the advantages and limitations of aerial photo-based tree mortality mapping. The proposed …
@article{cheng2024highresolution,
abstract = {Tree mortality has escalated worldwide in recent years due to climate warming and unprecedented drought events. However, mapping tree mortality across forest ecosystems has not yet been achieved. Aerial photos provide opportunities to reveal the spatial and spectral characteristics of canopy death at local to landscape scales. In this work, we present a deep learning model for mapping tree mortality from aerial photos in various forested ecosystems across Europe. This model builds on a baseline model trained with data on dead tree canopies from California using sub-meter resolution aerial photos and allows the use of various spatial resolutions of the input images (ranging from 10 to 60 cm). By comparing our results to ground observations and/or state-of-the-art forest disturbance and loss products, we will discuss the advantages and limitations of aerial photo-based tree mortality mapping. The proposed …},
added-at = {2024-11-29T11:48:11.000+0100},
author = {Cheng, Yan and Oehmcke, Stefan and Mosig, Clemens and Mirela, Beloiu and Kattenborn, Teja and Abel, Christin and Gominski, Dimitri and Nord-Larsen, Thomas and Fensholt, Rasmus and Horion, Stephanie},
biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/203c4532f40cfc512b881aa8e2b2fedce/joum576e},
citation = {EGU24, 2024},
interhash = {618bdd7d242b2e9c6558eeb23c361fed},
intrahash = {03c4532f40cfc512b881aa8e2b2fedce},
keywords = {imported topic_earthenvironment},
number = {EGU24-20213},
publisher = {Copernicus Meetings},
timestamp = {2024-11-29T11:48:11.000+0100},
title = {High-resolution mapping of tree mortality in European forests},
year = 2024
}
