Advances, challenges and a developing synthesis of ecological community assembly theory

Abstract

Ecological approaches to community assembly have emphasized the interplay between neutral processes, niche-based environmental filtering and niche-based species sorting in an interactive milieu. Recently, progress has been made in terms of aligning our vocabulary with conceptual advances, assessing how trait-based community functional parameters differ from neutral expectation and assessing how traits vary along environmental gradients. Experiments have confirmed the influence of these processes on assembly and have addressed the role of dispersal in shaping local assemblages. Community phylogenetics has forged common ground between ecologists and biogeographers, but it is not a proxy for trait-based approaches. Community assembly theory is in need of a comparative synthesis that addresses how the relative importance of niche and neutral processes varies among taxa, along environmental gradients, and across scales. Towards that goal, we suggest a set of traits that probably confer increasing community neutrality and regionality and review the influences of stress, disturbance and scale on the importance of niche assembly. We advocate increasing the complexity of experiments in order to assess the relative importance of multiple processes. As an example, we provide evidence that dispersal, niche processes and trait interdependencies have about equal influence on trait-based assembly in an experimental grassland.

Figure 1.

Summary diagram of a structural equation model describing the relative influence of dispersal history, trait interdependencies and niche processes on community mean values of four functional traits in an experimental grassland. The average standardized path coefficients are shown. The total effect of dispersal history when combined into a conceptual construct is shown with a dot-dashed line, while the total effect of trait interdependencies is shown with a dashed line. Measured variables are in rectangles, composite variables are in rounded boxes and latent variables are in ellipses.