Balancing model complexity is a key challenge of modern computational ecology, particularly so since the spread of machine learning algorithms. Species distribution models are often implemented using a wide variety of machine learning algorithms that can be fine‐tuned to achieve the best model prediction while avoiding overfitting. We have released
SDMtune
, a new R package that aims to facilitate training, tuning, and evaluation of species distribution models in a unified framework. The main innovations of this package are its functions to perform data‐driven variable selection, and a novel genetic algorithm to tune model hyperparameters. Real‐time and interactive charts are displayed during the execution of several functions to help users understand the effect of removing a variable or varying model hyperparameters on model performance.
SDMtune
supports three different metrics to evaluate model performance: the area under the receiver operating characteristic curve, the true skill statistic, and Akaike's information criterion corrected for small sample sizes. It implements four statistical methods: artificial neural networks, boosted regression trees, maximum entropy modeling, and random forest. Moreover, it includes functions to display the outputs and create a final report.
SDMtune
therefore represents a new, unified and user‐friendly framework for the still‐growing field of species distribution modeling.
Species inhabiting mountain ecosystems are expected to be particularly vulnerable to environmental change, yet information on their basic ecology is often lacking. Knowledge from field‐based empirical studies remains essential to refine our understanding of the impact of current habitat alterations and for the consequential development of meaningful conservation management strategies. This study focuses on a poorly investigated and vulnerable mountain bird species in Europe, the Ring Ouzel Turdus torquatus. Our aim was to identify the species’ key ecological requirements during the crucial period of nestling provisioning in the context of environmental change. We radiotracked and observed Alpine Ring Ouzels in a high‐density population, investigating their pattern of foraging habitat selection in 2015 and 2017, and evaluated the transferability of these results over a wider geographical range across the SW Swiss Alps. Foraging birds selected, consistently in space and time, short grass swards (< 10 cm) with interspersed patches of accessible and penetrable soils, at intermediate moisture levels (around 40–65% volumetric water content). In Alpine ecosystems, this microhabitat configuration is typically widespread during the spring snowmelt, but extremely seasonal, with a rapid decrease in its availability over the course of the breeding season. This underlines the high vulnerability of the Ring Ouzel to environmental change: an earlier snowmelt could generate a temporal mismatch between the peak of the breeding effort and optimal foraging conditions; however, abandoning grazing activities on semi‐wooded Alpine pastures may further decrease foraging habitat suitability through taller and denser grass swards, and subsequent woody vegetation encroachment. This study provides a mechanistic appraisal of the challenges Ring Ouzels will face in the future, as well as initial guidelines for targeted habitat management within timberline ecotones.
Mountain ecosystems naturally experience strong seasonal weather variations leading to a brief peak in food availability that constrains bird reproduction. Climate change accentuates both the intra‐ and interannual weather variability, which in turn can reduce the predictability of food resources and hence impact population demography. Yet, relatively little is known about the influence of environmental factors on the breeding ecology of mountain birds. Here, we quantified the nestling diet and provisioning behaviour of the Alpine ring ouzel Turdus torquatus alpestris, an emblematic and declining thrush species typical of central European treeline ecotones, and relate these parameters to local weather conditions. Nests were monitored with camcorders to assess prey provisioning frequency and identify items delivered by parents to nestlings, as well as to estimate prey biomass. Our results indicate the prominence of earthworms (Lumbricidae) in the nestling diet, both in terms of abundance (80%) and biomass (90%). Elevated ambient temperatures negatively impacted both prey provisioning rates and biomass delivered to chicks by parents, while rainfall had a positive effect on the delivered biomass. The mean prey item biomass decreased throughout the breeding season, as did the proportion of earthworms in nestlings' diet. These findings highlight the key role played by local weather in parental provisioning behaviour, probably reflecting the low availability of the staple food source, earthworms, in warm and dry weather contexts. In particular, they underpin how climate alterations, notably increasing ambient temperatures and changing precipitation regimes, could impact mountain birds. Although effects on reproductive performance and population dynamics still ought to be studied, these results further our understanding of the ecological mechanisms potentially at play in the decline of wildlife inhabiting high‐elevation, climate‐sensitive ecosystems.
This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
Mountains naturally offer variable habitat conditions, but their biodiversity is currently facing the extra challenge of adapting to rapid environmental shifts that are much more pronounced than in the lowlands. Among adaptive responses, intra‐ and inter‐seasonal movements represent potentially important coping strategies for wildlife that remain largely unexplored. We investigated the seasonal and daily movements of the ring ouzel Turdus torquatus, a European mountain bird species that is declining in many parts of its distribution. We tracked individuals breeding in the Swiss Alps using light‐level geolocators and multi‐sensor loggers. Of the birds traced to their non‐breeding grounds, two‐thirds reached the Atlas Mountains while one‐third stayed in Spain, a region potentially more significant for overwintering than previously thought. The birds remained mostly above 1000 m throughout the annual cycle, highlighting a strict association of ring ouzels with mountain habitats. We also evidenced flexible daily elevational movements, especially upon spring arrival on the breeding grounds in relation to date and snowfall occurrence, suggesting adaptive potential in response to environmental variation. This study shows how modern technology can deliver deeper and valuable insights into movements, behavioural patterns and life‐history strategies for relatively little‐studied animal species. By doing so, it paves the way for refined assessments of species' vulnerability to ongoing global change while providing basic conservation guidance.
Alpine ecosystems represent varied climates and vegetation structures globally, with the potential to support rich and functionally diverse avian communities. High mountain habitats and species are under significant threat from climate change and other anthropogenic factors. Yet, no global database of alpine birds exists, with most mountain systems lacking basic information on species breeding in alpine habitats, their status and trends, or potential cryptic diversity (i.e., sub-species distributions). To address these critical knowledge gaps, we combined published literature, regional monitoring schemes, and expert knowledge from often inaccessible, data-deficient mountain ranges to develop a global list of alpine breeding bird species with their associated distributions and select ecological traits. This dataset compiles alpine breeding records for 1,310 birds, representing 12.0% of extant species and covering all major mountain regions across each continent, excluding Antarctica. The Global Alpine Breeding Bird dataset (GABB) is an essential resource for research on the ecological and evolutionary factors shaping alpine communities, as well as documenting the value of these high elevation, climate-sensitive habitats for conserving biodiversity.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.