The spatial scaling of food web structure across European biogeographical regions

Abstract

The species-area relationship (SAR) is one of the most well-established scaling patterns in ecology. Its implications for understanding how communities change across spatial gradients are numerous, including the effects of habitat loss on biodiversity. However, ecological communities are not mere collections of species. They are the result of interactions between these species forming complex networks that tie them together. Should we aim to grasp the spatial scaling of biodiversity as a whole, it is fundamental to understand the changes in the structure of interaction networks with area. In spite of a few empirical and theoretical studies that address this challenge, we still do not know much about how network structure changes with area, or what are the main environmental drivers of these changes. Here, using the meta-network of potential interactions between all terrestrial vertebrates in Europe (1140 species and 67 201 feeding interactions), we analysed network-area relationships (NARs) that summarize how network properties scale with area. We do this across ten biogeographical regions, which differ in environmental characteristics. We found that the spatial scaling of network complexity strongly varied across biogeographical regions. However, once the variation in SARs was accounted for, differences in the shape of NARs vanished. On the other hand, the proportion of species across trophic levels remained remarkably constant across biogeographical regions and spatial scales, despite the great variation in species richness. Spatial variation in mean annual temperature and habitat clustering were the main environmental determinants of the shape of both SARs and NARs across Europe. Our results suggest new avenues in the exploration of the effects of environmental factors on the spatial scaling of biodiversity. We argue that NARs can provide new insights to analyse and understand ecological communities.

Keywords: food webs; geographical variation; metaweb; network–area relationship; spatial scale; species–area relationship; terrestrial vertebrate communities.

Figure 1

Study area. European biogeographical regions, as defined by the European Environmental Agency (<www.eea.europa.eu/data-and-maps/data/>; accessed on March 2020), considered in our analyses of the geographical variation in the spatial scaling of biodiversity.

Figure 2

The spatial scaling of network complexity properties across biogeographical regions in Europe. (a) Number of species, (b) links, (c) links per species, (d) mean generality (e) mean vulnerability, (f) standard deviation of generality and (g) standard deviation of vulnerability increase differently with area size across biogeographical regions (colour lines). Yet, total area and maximum values of network properties differ among biogeographical regions, which increases the visual differences between them. For a detailed description of the network properties see Methods. Lines represent a generalized additive model fit to data points. See the Supporting information for figure with data points.

Figure 3

Scale-invariant network properties. Relationship of the percentage of (a) basal, (b) intermediate and (c) top species with area and consumers’ diet overlap across biogeographical regions in Europe. The proportions of species per trophic level showed similar values across spatial scales and across biogeographical regions. Lines represent a generalized additive model fit to data points. Supporting information for figure with data points.

Figure 4

Relationship of network properties with species richness across biogeographical regions in Europe. Network complexity properties, i.e. (a) number of links, (b) links per species, (c) mean generality, (d) mean vulnerability, (e) standard deviation of generality and (f) standard deviation of vulnerability, strongly correlated with species richness in all biogeographical regions. In contrast, vertical diversity properties, i.e. (g) proportion of basal, (h) intermediate, (h) top species and (j) consumers’ diet overlap, do not correlate with species richness. Not every bioregion has the same number of species and, therefore, some are not represented along the whole range of species richness.

Figure 5

Relationship between habitat heterogeneity and temperature variability, and the scaling of SARs. Linear regression between (a) habitat clustering (quantified as Moran’s I) and (b) spatial variability in the mean annual temperature (quantified as the standard deviation of the mean annual temperature) across European bioregions, and the scaling exponent (z) of species-area relationships within them. Linear regression between response and predictors is given by: y = 0.54x₁ + 0.06x₂. R² = 0.83, p < 0.01 on 7 degrees of freedom. Each point represents a bioregion and lines are predictions from linear regression models.