RIASSUNTO
This paper introduces four representative machine learning (ML) methods, i.e., random forest, MaxEnt, support vector machine and artificial neural network and reviews their application in species' distribution modelling (SDM), an inherently interdisciplinary field that requires close collaboration between ecologists and data scientists. The benefits and flaws of these ML methods are discussed in detail with several examples of contemporary SDM studies. To enhance practice efficiency in applying ML in SDM, a framework for division of work load between the two scientific communities is proposed. A better predictive power can be derived from hybrid ML approaches, such as ensemble learning. The deep learning method, however, has been largely underdeveloped in this field. Albeit challenging, the vast potential of applying deep learning in SDM needs to be seen, especially in an increasingly data-rich and open-access world.