EGU23-9939, updated on 26 Feb 2023
EGU General Assembly 2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Mapping storm damage across the world’s forests

Nezha Acil1,2, Joseph Wayman1, Susanne Suvanto1,3, Cornelius Senf4, Jonathan Sadler1, and Thomas Pugh1,5
Nezha Acil et al.
  • 1Birmingham Institute of Forest Research, School of Geography Earth & Environmental Sciences, University of Birmingham, Birmingham, United Kingdom
  • 2National Centre of Earth Observation, School of Geography Geology and the Environment, University of Leicester, Leicester, United Kingdom
  • 3Natural Resources Institute Finland (Luke), Latokartanonkaari, Helsinki, Finland
  • 4Ecosystem dynamics and forest management group, Technical University of Munich, Freising, Germany
  • 5Department of Physical Geography and Ecosystem Science, Lund University, Lund, Sweden

Storms are natural weather events, varying greatly in frequency and intensity across the world. They are characterised by strong winds that can disturb forests via tree defoliation, breakage and uprooting. Despite close monitoring of forest disturbance occurrences in recent years, we still lack information on the contribution of storms in driving forest dynamics worldwide. Here, we build a machine learning classification model to identify wind-related forest disturbances at the global scale. Forest disturbance patches detected between 2002 and 2014 were associated with multiple covariates as potential indicators of wind damage. These covariates include structural metrics inherent to the disturbances, such as patch size, elongation and spatiotemporal clustering, as well as environmental variables describing topography, weather, and soil conditions. We used these data for 20,000 reference patches (10,000 wind and 10,000 non-wind), widely distributed across forest biomes, to train a random forest classifier. Cross-validation with 20,000 other reference patches over 10 runs showed that the model achieved satisfactory performance scores. It yielded omission errors of ca. 20% and commission errors of ca. 5%, mostly associated with harvest, selective logging and biotic outbreaks.  The most important variable was maximum wind speed, followed by patch temporal clustering. Model deployment at the global scale will provide quantitative insights into storm damage biogeography, regime characteristics and relative contributions to global carbon fluxes and forest dynamics.

How to cite: Acil, N., Wayman, J., Suvanto, S., Senf, C., Sadler, J., and Pugh, T.: Mapping storm damage across the world’s forests, EGU General Assembly 2023, Vienna, Austria, 24–28 Apr 2023, EGU23-9939,, 2023.