Use of machine learning techniques to model wind damage to forests

Publications
Published on

This paper tested the ability of machine learning techniques, namely artificial neural networks and random forests, to predict the individual trees within a forest most at risk of damage in storms. Models based on these techniques were developed individually for both a small forest area containing a set of 29 permanent sample plots that were damaged in Storm Martin in December 1999, and from a much larger set of 235 forest inventory plots damaged in Storm Klaus in January 2009. Both data sets are within the Landes de Gascogne Forest in Nouvelle-Aquitaine, France. The models were tested both against the data from which they were developed, and against the data set from the other storm.

For comparison with an earlier study using the same data, logistic regression models were also developed. In addition, the ability of machine learning techniques to substitute for a mechanistic wind damage risk model by training them with previous mechanistic model predictions was tested

Highlights

  • Machine learning techniques were accurate in predicting wind damage to trees.
  • Random forests proved the most accurate and discriminating methodology.
  • Models were sensitive to removal of site and stand but not tree characteristics
  • All models were able to accurately replicate a mechanistic wind risk model.
  • Machine learning techniques could help the management of wind damage to forests.

Authors

Emma Hart, Kevin Sim, Kana Kamimura, Céline Meredieu, Dominique Guyon, Barry Gardiner

Keywords

  • Machine learning
  • Forest damage
  • Wind risk
  • Risk models
  • GALES
  • Forest planning

 

Read the full paper here