Aim: Species distribution models (SDMs) have emerged as essential tools in the equipment of many ecologists, useful to explore species distributions in space and time and answering an assortment of questions related to biogeography, climate change biology and conservation biology. Historically, most SDM research concentrated on well‐known organisms, especially vertebrates. In recent years, these tools are becoming increasingly important for predicting the distribution of understudied invertebrate taxa. Here, we reviewed the literature published on main terrestrial arthropod predators (ants, ground beetles and spiders) to explore some of the challenges and opportunities of species distribution modelling in mega‐diverse arthropod groups.Location: Global.Methods: Systematic mapping of the literature and bibliometric analysis.Results: Most SDM studies of animals to date have focused either on broad samples of vertebrates or on arthropod species that are charismatic (e.g. butterflies) or economically important (e.g. vectors of disease, crop pests and pollinators). We show that the use of SDMs to map the geography of terrestrial arthropod predators is a nascent phenomenon, with a near‐exponential growth in the number of studies over the past ten years and still limited collaborative networks among researchers. There is a bias in studies towards charismatic species and geographical areas that hold lower levels of diversity but greater availability of data, such as Europe and North America.Conclusions: Arthropods pose particular modelling challenges that add to the ones already present for vertebrates, but they should also offer opportunities for future SDM research as data and new methods are made available. To overcome data limitations, we illustrate the potential of modern data sources and new modelling approaches. We discuss areas of research where SDMs may be combined with dispersal models and increasingly available phylogenetic and functional data to understand evolutionary changes in ranges and range‐limiting traits over past and contemporary time‐scales.

Fishing spiders (Dolomedes spp.) make an interesting model to predict the impact of global changes because they are generalist, opportunistic predators, whose distribution is driven mostly by abiotic factors. Yet, the two European species are expected to react differently to forthcoming environmental changes, because of habitat specialization and initial range. We used an original combination of habitat and dispersal data to revisit these predictions under various climatic scenarios. We used the future range of suitable habitat, predicted with habitat variables only, as a base layer to further predict the range or reachable habitat by accounting for both dispersal ability and landscape connectivity. Our results confirm the northward shift in range and indicate that the area of co-occurrences should also increase. However, reachable habitat should expand less than suitable habitat, especially when accounting for landscape connectivity. In addition, the potential range expansion was further limited for the red-listed D. plantarius, which is more of a habitat specialist and has a lower ability to disperse. This study highlights the importance of looking beyond habitat variables to produce more accurate predictions for the future of arthropods populations.

Land cover data are commonly used to model the terrestrial carbon (C) sink, yet these data have wide margins of error that significantly alter estimates of global C storage. Here we demonstrate this data vulnerability in grasslands, which are critical to C cycling but whose estimated distribution has varied by >50 million km ² (3.5–42% of the Earth’s terrestrial surface). Comparing multiple high-resolution land cover products with expertly annotated grassland data from six continents, we show sources of mapping error and discuss C implications based on 2023 United Nations (UN) FAO estimates. Past misidentification arose from inconsistent definitions on grassland identity and classification flaws especially relating to woody plant cover. Correcting these errors adjusted grassland coverage to 22.8% of the terrestrial land base (30.1 million km ² ), elevating UN projections of soil C stocks to 155.02 Pg (0–30 cm depth). These findings underscore the challenges of biome mapping for ecosystem accounting and policy, when lacking field-validated remotely sensed data.

Dispersal abilities are important to support metapopulation functioning and species distributions, yet it is rarely accounted for in conservation. Here, we compared the propensity for dispersal between the two fishing spiders present in Europe: the widespread habitat‐generalist Dolomedes fimbriatus and the scarcer red‐listed Dolomedes plantarius. We experimentally tested for airborne and waterborne dispersal using first instar juveniles sampled in nursery webs, and older juveniles. We estimated the propensity for short and long‐distance dispersal of airborne and waterborne behaviours, and we tested the difference between species with generalised linear mixed models. Airborne (ballooning) and waterborne (sailing) behaviours were more frequent for D. fimbriatus than for D. plantarius , indicating a higher propensity of the former for long‐distance dispersal. The frequency of rappelling behaviour, and thus the propensity for short‐distance dispersal, did not differ between species. However, we found contrasting results for short‐distance dispersal on the water, with rowing being more frequent and running less frequent for D. plantarius than for D. fimbriatus . The different propensity for dispersal between the two species might be partly explained by the ecology of D. plantarius , which is known to be more habitat‐specialist and more dependent to water bodies than D. fimbriatus. The limited propensity for dispersal of the red‐listed D. plantarius is another argument for conserving an interconnected network of wetlands in Fennoscandia. Indeed, increased isolation of populations would be detrimental for species maintenance.

High‐resolution unoccupied aerial vehicle (UAVs) data have alleviated the mismatch between the scale of ecological processes and the scale of remotely sensed data, while machine learning and deep learning methods allow new avenues for quantification in ecology. Ant nests play key roles in ecosystem functioning, yet their distribution and effects on entire landscapes remain poorly understood, in part because they and their mounds are too small for satellite remote sensing. This research maps the distribution and impact of ant mounds in a 20 ha treeline ecotone. We evaluate the detectability from UAV imagery using a deep learning model for object detection and different combinations of RGB, thermal and multispectral sensor data. We were able to detect ant mounds in all imagery using manual detection and deep learning. However, the highest precision rates were achieved by deep learning using RGB data which has the highest spatial resolution (1.9 cm) at comparable UAV flight height. While multispectral data were outperformed for detection, it allows for novel insights into the ecology of ants and their spatial impact on vegetation productivity using the normalized difference vegetation index. Scaling up, this suggests that ant mounds quantifiably impact vegetation productivity for up to 4% of our study area and up to 8% of the Betula nana vegetation communities, the vegetation type with the highest abundance of ant mounds. Therefore, they could have an overlooked role in nutrient‐limited tundra vegetation, and on the shrubification of this habitat. Further, we show the powerful combination UAV multi‐sensor data and deep learning for efficient ecological tracking and monitoring of mound‐building ants and their spatial impact.

Wetlands are among the most threatened habitats in the world, and so are their species, which suffer habitat loss due to climate and land use changes. Freshwater species, and especially arthropods, receive comparatively little attention in conservation plans, and the goals to stop and reverse the destruction of wetlands published 25 years ago in a manifesto by the Union of Concerned Scientists have not been reached. In this study, we investigated the occurrence and habitat requirements at two spatial scales of two species of European fishing spiders Dolomedes, which rely heavily on declining wetland habitats in Sweden and southern Norway. We collected occurrence data for Dolomedes plantarius and Dolomedes fimbriatus, using a live-determination method. We modelled the placement of nursery webs to describe fine-scale habitat requirements related to vegetation and micro-climate. Using a machine learning approach, we described the habitat features for each species and for co-occurrence sites, thus providing insight into variables relevant for the presence and detectability of Dolomedes. Nursery placement is mostly dependent on proximity to water, presence of Carex sp. (Sedges) and crossing vegetation structures, and on humidity, while detection can be affected by weather conditions. Furthermore, co-occurrence sites were more similar to D. plantarius sites than to D. fimbriatus sites, whereby surrounding forest, water type and velocity, elevation and latitude were of importance for explaining which species of Dolomedes was present. Overall, habitat requirements were narrower for D. plantarius compared to D. fimbiratus.