EGU23-5917, updated on 22 Feb 2023
EGU General Assembly 2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Mapping and characterising tree mortality in California at individual tree level using deep learning

Yan Cheng1, Stefan Oehmcke2, Martin Brandt1, Adrian Das3, Lisa Rosenthal3, Sassan Saatchi4,5, Fabien Wagner4,5, Wim Verbruggen1, Anton Vrieling6, Claus Beier1, and Stephanie Horion1
Yan Cheng et al.
  • 1Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark
  • 2Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
  • 3US Geological Survey, Western Ecological Research Center, Three Rivers, Sequoia and Kings Canyon Field Station, California, USA
  • 4University of California, Los Angeles, USA
  • 5Propulsion Laboratory, California Institute of Technology, Pasadena, USA
  • 6Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, Enschede, the Netherlands

Tree mortality caused by natural disturbances, such as droughts, insects, and wildfires, is a global issue due to increased frequency and severity of extreme weather. California has been a major hotspot of large-scale tree mortality since 2012-2015 drought. Despite many local studies, there is no confident count of dead trees at the state level. Here we mapped all individual dead trees in California using submeter aerial images and Conventional Neural Network (i.e. EfficientUnet architecture). The model accuracy is about 96% and 83% when comparing to visually interpreted samples from aerial photos and in-situ observations, respectively. In total, we found more than 80 million dead trees from NAIP imagery in 2020, which accounts for 2% of trees reported in 2011. About half of the dead trees belongs to California mixed conifer group. North coast and central and southern Serrie Nevada are the most affected regions. Based on the localization and segmentation of every single dead tree, we retrieved mortality traits (i.e. dead tree density, dead crown size, and classification of old or recent death) and identified hotspots that have emerging mortality and high wildfire fuel load. The mortality traits, along with individual dead tree location at the state scale, provides unprecedented detailed information for forest management and improved carbon accounting, helping to understand dynamics and causes of tree mortality in a changing climate.

How to cite: Cheng, Y., Oehmcke, S., Brandt, M., Das, A., Rosenthal, L., Saatchi, S., Wagner, F., Verbruggen, W., Vrieling, A., Beier, C., and Horion, S.: Mapping and characterising tree mortality in California at individual tree level using deep learning, EGU General Assembly 2023, Vienna, Austria, 24–28 Apr 2023, EGU23-5917,, 2023.