Negative biotic interactions drive predictions of distributions for species from a grassland community

Abstract

Understanding the factors that determine species' geographical distributions is important for addressing a wide range of biological questions, including where species will be able to maintain populations following environmental change. New methods for modelling species distributions include the effects of biotic interactions alongside more commonly used abiotic variables such as temperature and precipitation; however, it is not clear which types of interspecific relationship contribute to shaping species distributions and should therefore be prioritized in models. Even if some interactions are known to be influential at local spatial scales, there is no guarantee they will have similar impacts at macroecological scales. Here we apply a novel method based on information theory to determine which types of interspecific relationship drive species distributions. Our results show that negative biotic interactions such as competition have the greatest effect on model predictions for species from a California grassland community. This knowledge will help focus data collection and improve model predictions for identifying at-risk species. Furthermore, our methodological approach is applicable to any kind of species distribution model that can be specified with and without interspecific relationships.

Keywords: biotic interactions; minimum description length principle; model selection; normalized maximum likelihood; species distribution models; species geographical ranges.

Figure 1.

Workflow for generating community distribution matrices. The starting point is a matrix of prior habitat suitability values (HSVs) that reflect only abiotic conditions for each species (columns) at distinct locations (rows). We then use a Bayesian network to modify prior HSVs to give posterior HSVs that also include the effects of interspecific relationships on species distributions. For each species and both HSV matrices separately, we specify thresholds to convert prior and posterior HSVs to binary ranges.

Figure 2.

Workflow for measuring the effect of interspecific relationships on community distribution matrices. For each prior and posterior matrix, we calculate total length for a compression model with no interspecific relationships (‘Empty BN’), and total length for a compression model, M, representing a subset of the interspecific relationships used to generate the posterior community distribution matrix. A particular subset of interspecific relationships can be said to significantly influence range predictions if model M compresses the posterior community distribution matrix more than the Empty BN, and the increase in compression is greater than the comparable increase with the prior community distribution matrix.