Journal Article

Application of machine learning methods in forest ecology: recent progress and future challenges

Liu, Zelin, Peng, Changhui, Work, Timothy, Candau, Jean-Noel, DesRochers, Annie, Kneeshaw, Daniel

2018

Overview

Machine learning, an important branch of artificial intelligence, is increasingly being applied sciences such as forest ecology. Here, we review and discuss three commonly used methods of machine learning including decision tree learning, artificial neural network, and support vector machine, and their applications in five different aspects of forest ecology over the last decade. These applications include: (1) species distribution models (SDMs), (2) carbon cycles, (3) hazard assessment and prediction, and (4) other applications in forest management. While machine learning approaches are useful for classification, modeling, and prediction in forest ecology research, further expansion of machine learning technologies is limited by the lack of suitable data and the relatively “higher threshold” of applications. However, the combined use of multiple algorithms and improved communication and cooperation between ecological researchers and machine learning developers still present major challenges and tasks for the betterment of future ecological research. We suggest that future applications of machine learning in ecology will become an increasingly attractive tool for ecologists in the face of “big data” and that ecologists will gain access to more types of data such as sound and video in the near future possibly opening new avenues of research in forest ecology.

• Publisher: University of Toronto,NRC Research Press
• Subject: apprentissage par arbres décisionnels / artificial neural network / classification des espèces / decision support systems / decision-trees learning / forest ecology / Forest management / geographical distribution / gestion forestière / hazard assessment / hazard characterization / Machine learning / machine à vecteurs de support / neural networks / prediction / réseau de neurones artificiels / species classification / support vector machine / support vector machines / Technology application / évaluation des dangers