Search

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. • Machine learning (ML) use in conservation is expected to grow as datasets expand. • Maximum entropy and Bayesian ML methods are the most popular in this domain. • Neural networks are powerful but have limited use due to lack of interpretability. • Most common ML use is in niche modelling, assisted decision making, and monitoring. • Care must be taken to choose the ML model as its characteristics can be limiting. [ABSTRACT FROM AUTHOR]

Animal parasites are species rich and ecologically diverse, some with complex life cycles and life histories and consequently many are vulnerable to extinction. While the conservation biology community is becoming cognisant of the plight of threatened parasites, coupled at times with potential host co-extinction, feasible criteria have not been developed to specifically assess their threat risk and methods to conserve them have also received limited attention. Methodologies and criteria are presented here to aid the assessment of the conservation status of threatened parasites in a way consistent with the criteria of the International Union for the Conservation of Nature (IUCN). Such assessments assist in prioritizing conservation efforts, a crucial task given parasites are integral to the functioning and survival of global ecosystems. • Animal parasites are ecologically important and highly vulnerable to extinction. • Available conservation rubrics are poorly suited for assessing animal parasites. • The first assessment framework designed for animal parasites is presented. • Widescale assessments of the conservation status of animal parasites can now occur. [ABSTRACT FROM AUTHOR]

Species differ in their biological susceptibility to extinction, but the set of traits determining susceptibility varies across taxa. It is yet unclear which patterns are common to all taxa, and which are taxon-specific, with consequences to conservation practice. In this study we analysed the generality of trait-based prediction of extinction risk across terrestrial (including freshwater) vertebrates, invertebrates and plants at a global scale. For each group, we selected five representative taxa and within each group we explored whether risk can be related to any of 10 potential predictors. We then synthesized outcomes across taxa using a meta-analytic approach. High habitat specificity was a consistent predictor across vertebrates, invertebrates and plants, being a universal predictor of risk. Slow life-history traits – large relative offspring size, low fecundity, long generation length –, and narrow altitudinal range were also found to be good predictors across most taxa, but their universality needs to be supported with additional data. Poor dispersal ability was a common predictor of extinction risk among invertebrate and plant taxa, but not consistently among vertebrates. The remaining traits (body size, microhabitat verticality, trophic level, and diet breadth) were useful to predict extinction risk but only at lower taxonomical levels. Our study shows that despite the idiosyncrasies among taxa, universal susceptibility to extinction exists and several traits might influence extinction risk for most taxa. Informing conservation prioritization at lower taxonomic scales should however include taxon-specific trait-based predictors of extinction risk. [ABSTRACT FROM AUTHOR]