Abstract Metawebs (networks of potential interactions within a species pool) are a powerful abstraction to understand how large‐scale species interaction networks are structured. Because metawebs are typically expressed at large spatial and taxonomic scales, assembling them is a tedious and costly process; predictive methods can help circumvent the limitations in data deficiencies, by providing a first approximation of metawebs. One way to improve our ability to predict metawebs is to maximize available information by using graph embeddings, as opposed to an exhaustive list of species interactions. Graph embedding is an emerging field in machine learning that holds great potential for ecological problems. Here, we outline how the challenges associated with inferring metawebs line‐up with the advantages of graph embeddings; followed by a discussion as to how the choice of the species pool has consequences on the reconstructed network, specifically as to the role of human‐made (or arbitrarily assigned) boundaries and how these may influence ecological hypotheses.

Human-mediated dispersal is a major contributor of biological invasions. To reduce impacts induced by the introduction and spread of exotic species, biosecurity interventions are put into place. These interventions often rely on risk-assessment procedures, whereby biosecurity practitioners (which includes researchers, stakeholders such as national park managers, and all other decision makers who determine when and how to protect biodiversity) attempt to preemptively identify and predict which exotic species could potentially become a threat to natural ecosystems. In theory, extensive field and experimental studies would be required to accurately and precisely determine the risks of biological invasion of a species or group of species. However, due to a lack of resources or knowledge, such critical studies are limited. As a result, biosecurity practitioners rarely have a full picture of the extent to which the exotic species has and will spread at the time of decision making. Hence, they instead opt for preventive measures such as identifying and managing potential target exotic species which are likely to be invasive or dispersal pathways through which exotic species are likely to be introduced and spread. As most of the uncertainties pertaining to biosecurity interventions lie in the resolution of data made available to practitioners at the time of decision making, we first present some of the different types of information which are readily available during the risk-assessment procedure. We then highlight how one could exploit these different resolutions of data during the risk-assessment procedure using network analysis to better understand human-mediated dispersal of exotic species. By doing so, our paper puts forward what network analysis has to offer practitioners in the context of biosecurity interventions.

Networks are increasingly used in various fields to represent systems with the aim of understanding the underlying rules governing observed interactions, and hence predict how the system is likely to behave in the future. Recent developments in network science highlight that accounting for node metadata improves both our understanding of how nodes interact with one another, and the accuracy of link prediction. However, to predict interactions in a network within existing statistical and machine learning frameworks, we need to learn objects that rapidly grow in dimension with the number of nodes. Thus, the task becomes computationally and conceptually challenging for networks. Here, we present a new predictive procedure combining a statistical, low-rank graph embedding method with machine learning techniques which reduces substantially the complexity of the learning task and allows us to efficiently predict interactions from node metadata in bipartite networks. To illustrate its application on real-world data, we apply it to a large dataset of tourist visits across a country. We found that our procedure accurately reconstructs existing interactions and predicts new interactions in the network. Overall, both from a network science and data science perspective, our work offers a flexible and generalizable procedure for link prediction.

Metawebs, i.e. networks of potential interactions within a species pool, are a powerful abstraction to understand how large-scales species interaction networks are structured.Because metawebs are typically expressed at large spatial and taxonomic scales, assembling them is a tedious and costly process; predictive methods can help circumvent the limitations in data deficiencies, by providing ‘draft’ metawebs.One way to improve the predictive ability is to maximize the information used for prediction, by using graph embeddings rather than the list of species interactions. Graph embedding is an emerging field in machine learning that holds great potential for ecological problems.In this perspective, we outline how the challenges associated with inferring metawebs line-up with the advantages of graph embeddings; furthermore, because metawebs are inherently spatial objects, we discuss how the choice of the species pool has consequences on the reconstructed network, but also embeds hypotheses about which human-made boundaries are ecologically meaningful.

Despite their importance in many ecological processes, collecting data and information on ecological interactions is an exceedingly challenging task. For this reason, large parts of the world have a data deficit when it comes to species interactions and how the resulting networks are structured. As data collection alone is unlikely to be sufficient, community ecologists must adopt predictive methods. We present a methodological framework that uses graph embedding and transfer learning to assemble a predicted list of trophic interactions of a species pool for which their interactions are unknown. Specifically, we ‘learn’ the information (latent traits) of species from a known interaction network and infer the latent traits of another species pool for which we have no a priori interaction data based on their phylogenetic relatedness to species from the known network. The latent traits can then be used to predict interactions and construct an interaction network. Here we assembled a metaweb for Canadian mammals derived from interactions in the European food web, despite only 4% of common species being shared between the two locations. The results of the predictive model are compared against databases of recorded pairwise interactions, showing that we correctly recover 91% of known interactions. The framework itself is robust even when the known network is incomplete or contains spurious interactions making it an ideal candidate as a tool for filling gaps when it comes to species interactions. We provide guidance on how this framework can be adapted by substituting some approaches or predictors in order to make it more generally applicable.

Human visitors are associated with the unintended dispersal of weeds, seeds and pathogens across ecological communities. With the increasing popularity of nature-based tourism, access to protected areas has increased, in turn increasing the risks of unintended dispersal of exotic species to these areas. Here, we assess the potential contribution of both international and domestic visitors travelling within New Zealand to the spread of exotic species. To get an overview of the visitors' travelling patterns across the country, we constructed visitation networks at two spatial scales-a regional scale (which is a coarse scale) and a local territorial scale (which is a finer scale). We then used a Mixed Membership Stochastic Block Model to identify characteristic groups of visitors and places based on the similarities of the visitors' travelling patterns across the country. Overall, we found that there are 10 characteristic groups of visitors travelling to 12 characteristic groups of places at the regional scale and 6 characteristic groups of visitors travelling to 6 characteristic groups of places at the territorial scale. The resulting characteristic travelling patterns of the visitors across New Zealand further allowed us to estimate the different visitor groups' likelihood to travel to protected areas. Overall, we found that some visitor groups are much more likely than others to travel to protected areas of high protection status, at both spatial scales. Synthesis and applications. Our results highlight the importance of accounting for human behaviour-that is, understanding how visitors travel to places-when assessing human-mediated dispersal. More specifically, we illustrate how to assess the relative contribution of a potential vector dispersing exotic species based on their travelling patterns-especially in cases where the target exotic species are not yet identified or when there is limited information regarding the dispersal routes of exotic species and their potential vectors. As a result, our work offers a holistic perspective on human-mediated dispersal of exotic species. Moreover, it provides a potential baseline against which both field biologists and practitioners can identify areas that would benefit from further investigation to better understand invasion processes in their focal systems.

Biological interactions are key drivers of ecological and evolutionary processes. The complexity of such interactions hinders our understanding of ecological systems and our ability to make effective predictions in changing environments. However, network analysis allows us to better tackle the complexity of ecosystems because it extracts the properties of an ecological system according to the number and distribution of links among interacting entities. The number of studies using network analysis to solve ecological and evolutionary questions in parasitology has increased over the past decade. Here, we synthesise the contribution of network analysis toward disentangling host-parasite processes. Furthermore, we identify current trends in mainstream ecology and novel applications of network analysis that present opportunities for research on host-parasite interactions.

Abstract There is a growing need for collaborative and interdisciplinary research in addressing global ecological challenges, and early career researchers (ECRs) often play a vital role in such ventures. But despite the desire for such approaches, forming new and interdisciplinary collaborations is risky, and disproportionately so for ECRs, whose perspectives on this topic are rarely heard. Here, we present common perceptions among ECRs regarding opportunities for intra‐ and interdisciplinary collaboration, and barriers preventing such collaboration from taking place. We also discuss possible solutions, and the ecological outcomes of fostering more collaboration. The perceptions discussed have been distilled from a two‐day workshop in New Zealand, aiming to investigate the potential for collaboration between 34 ECRs in distinct ecological disciplines across ten research institutes. Commonality in methodology or research aims was vital for potential collaborations to be considered worthwhile, but differences in spatial or temporal scales were a key disconnect that hindered numerous potential crossovers. Individual connectivity and institutional structures were commonly perceived as barriers to acting collaboratively in general. Specifically, barriers included having a small peer network, lack of access to funding, and concerns over the risk/reward ratio of forming new collaborations. Overcoming barriers will require active, practical support from institutions, funding bodies and mentors, and participants commonly called for specific funding support and the creation of ECR‐focused spaces to better foster collaborative behavior. Fostering interdisciplinary ECR collaborations in ecology was perceived to be useful in creating larger and more useful datasets and tools, and more scalable and transferable models and outcomes. Adopting practices that facilitate more ECR‐led interdisciplinary collaboration will help generate a more integrative understanding of ecological systems globally.