The use of machine learning in species threats and conservation analysis

The concepts and methodologies of machine learning are increasingly used to create semi-autonomous programmes capable of adapting to a multitude of problems and decision-making scenarios. With its potential in big data analysis, machine learning is particularly useful for tackling global conservation problems that often involve vast amounts of data and complex interactions between variables. In this systematic review, we summarise the use of machine learning methods in the study of species threats and conservation measures, and their emergent trends. Maximum entropy, Bayesian (regression or classification models) and ensemble methods (tree-based models, either bagging or boosting) have gained wide popularity in the past years and are now commonly used for multiple problems. Their relevance to modern conservation issues (and associated data types), their relatively simple implementation, and availability in a variety of software packages are the most likely factors to explain their popularity. Neural networks, decision trees, support-vector machines and evolutionary algorithms have been used in more specific situations, with some model applications showing promise in dealing with increasingly complex data and scenarios.

Automated summary

The concepts and methodologies of machine learning are increasingly used for creating semi-autonomous programmes that can adapt to various problems and decision-making scenarios. This systematic review summarizes the use of machine learning methods in studying species threats and conservation measures, and identifies the emerging trends. Maximum entropy, Bayesian models, ensemble methods, and other algorithms have gained popularity for various conservation problems due to their relevance, ease of implementation, and availability in software packages.