A hybrid method for feature construction and selection to improve wind-damage prediction in the forestry sector

Hart, Emma; Sim, Kevin; Gardiner, Barry; Kamimura, Kana

Abstract

Catastrophic damage to forests resulting from major storms has resulted in serious timber and financial losses within the sector across Europe in the recent past. Developing risk assessment methods is thus one of the keys to finding forest management strategies to reduce future damage. Previous approaches to predicting damage to individual trees have used mechanistic models of wind-flow or logistical regression with mixed results. We propose a novel filter-based Genetic Programming method for constructing a large set of new features which are ranked using the Hellinger distance metric which is insensitive to skew in the data. A wrapper-based feature-selection method that uses a random forest classifier is then applied predict damage to individual trees. Using data collected from two forests within SouthWest France, we demonstrate significantly improved classification results using the new features, and in comparison to previously published results. The feature-selection method retains a small set of relevant variables consisting only of newly constructed features whose components provide insights that can inform forest management policies.

Citation

Hart, E., Sim, K., Gardiner, B., & Kamimura, K. (2017). A hybrid method for feature construction and selection to improve wind-damage prediction in the forestry sector. In GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference (1121-1128). https://doi.org/10.1145/3071178.3071217

• Conference Name: Proceedings of the Genetic and Evolutionary Computation Conference on - GECCO '17
• Start Date: Jul 15, 2017
• End Date: Apr 19, 2017
• Acceptance Date: Mar 20, 2017
• Online Publication Date: Jul 1, 2017
• Publication Date: 2017
• Deposit Date: Apr 6, 2017
• Publicly Available Date: Jul 2, 2018
• Journal: Proceedings of the Genetic and Evolutionary Computation Con-ference 2017
• Publisher: Association for Computing Machinery (ACM)
• Volume: 8
• Issue: 17
• Pages: 1121-1128
• Book Title: GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference
• ISBN: 9781450349208
• DOI: https://doi.org/10.1145/3071178.3071217
• Keywords: Computing methodologies, search methodologies, genetic programming, KEYWORDS Feature-construction, Machine-Learning, Forestry
• Public URL: http://researchrepository.napier.ac.uk/Output/826213