Search

Wetlands, one of the most biodiverse ecosystems in the world, are increasingly subjected to area loss and degradation due to land-use and climate changes. These factors impact their unique biodiversity, including numerous invertebrates that depend on them. Here we investigated the current and future habitat suitability of the aquatic spiders Argyroneta aquatica and Dolomedes plantarius. We evaluated future trends in their geographic range, aiming at assessing their extinction risk according to the International Union for Conservation of Nature (IUCN) Red List criteria, at both global and regional levels. We investigated present and future distribution ranges using species distribution models for two integrated emission scenarios (SSP1-2.6 and SSP5-8.5) and combining three general circulation models. These were combined with knowledge on species' dispersal limitation to account for the possibility that these species will not be able to move beyond the current range in the next decades. We found a significant future northern shift in the geographic range and a global reduction in habitat suitability for both species, corresponding to a loss of 28.9 % for A. aquatica and 38.1 % for D. plantarius in the next 10 years. The application of the IUCN criteria qualifies A. aquatica as Near Threatened and D. plantarius as Vulnerable. Regional assessments provided similar patterns of range reductions and population vulnerability across all European regions, particularly for Central-Eastern and Western Europe. Conversely, Northern Europe is expected to become a climatic refugium for both species. This work goes beyond the available studies on the conservation of these species by taking account their dispersal abilities in quantifying future trends in their habitat suitability using the most up to date knowledge. Conservation strategies should be directed towards limiting the impact of climatic and non-climatic stressors on wetlands, and towards implementing management plans and restoration programmes to increase habitat suitability and connectivity among wetland patches. [Display omitted] • Argyroneta aquatica and Dolomedes plantarius are charismatic species of wetlands subjected to habitat loss and degradation. • A future northern shift in geographic range and a global reduction in habitat suitability is forecasted for both species. • The predicted loss is 28.9 % for A. aquatica and 38.1 % for D. plantarius in the next 10 years. • The application of the IUCN criteria qualifies A. aquatica as Near Threatened and D. plantarius as Vulnerable. • Regional assessments provided similar patterns of range reductions and population vulnerability across all European regions. [ABSTRACT FROM AUTHOR]

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]