A review of supervised machine learning algorithms and their applications to ecological data

作者：Crisci C; Ghattas B^*; Perera G

来源：Ecological Modelling, 2012, 240: 113-122.

DOI：10.1016/j.ecolmodel.2012.03.001

• Machine learning
• Ecological data
• Regression analysis
• Classification rules
• Prediction
• Mass mortality events
• Coastal rocky benthic communities
• Positive thermal anomalies

In this paper we present a general overview of several supervised machine learning (ML) algorithms and illustrate their use for the prediction of mass mortality events in the coastal rocky benthic communities of the NW Mediterranean Sea. In the first part of the paper we present, in a conceptual way, the general framework of ML and explain the basis of the underlying theory. In the second part we describe some outstanding ML techniques to treat ecological data. In the third part we present our ecological problem and we illustrate exposed ML techniques with our data. Finally, we briefly summarize some extensions of several methods for multi-class output prediction.

• 出版日期2012-8-10