Mutualisms weaken the latitudinal diversity gradient among oceanic islands

The latitudinal diversity gradient (LDG) dominates global patterns of diversity1,2, but the factors that underlie the LDG remain elusive. Here we use a unique global dataset3 to show that vascular plants on oceanic islands exhibit a weakened LDG and explore potential mechanisms for this effect. Our results show that traditional physical drivers of island biogeography4—namely area and isolation—contribute to the difference between island and mainland diversity at a given latitude (that is, the island species deficit), as smaller and more distant islands experience reduced colonization. However, plant species with mutualists are underrepresented on islands, and we find that this plant mutualism filter explains more variation in the island species deficit than abiotic factors. In particular, plant species that require animal pollinators or microbial mutualists such as arbuscular mycorrhizal fungi contribute disproportionately to the island species deficit near the Equator, with contributions decreasing with distance from the Equator. Plant mutualist filters on species richness are particularly strong at low absolute latitudes where mainland richness is highest, weakening the LDG of oceanic islands. These results provide empirical evidence that mutualisms, habitat heterogeneity and dispersal are key to the maintenance of high tropical plant diversity and mediate the biogeographic patterns of plant diversity on Earth.


Table of Contents
SI Table 1.

SI Table 1 | Model results for the latitudinal diversity gradient in plant species on mainlands and islands.
Model results for GLMs used to test for the LDG on mainlands and islands.The significance of the interaction between land type, in particular between mainlands and oceanic islands, and absolute latitude in (A) confirms that although there is a relationship between absolute latitude and species richness on mainlands, this is weakened on oceanic islands.Separate tests for the LDG on mainlands (B) and both island types separately (C, D) confirm that absolute latitude predicts a stronger reduction in species richness for mainlands and non-oceanic islands relative to oceanic islands.

SI Table 2 | Model results for drivers of island species deficit.
Model results for models used to test for drivers of island species deficit, including the influence of abiotic variables and the mutualism filter strength, including model averaging (A) and subsequent model selection via testing increasing interactions (B).The variable 'mututalism filter strength' here represents the proportion of mainland floras associating with any one of the three mutualisms included in our analyses (biotic pollination, arbuscular mycorrhizal, or Nfixing).

SI Table 3 | Model results for proportional specific deficit and contribution to species deficit for pollination mutualisms.
Model results for GLMs testing drivers of proportional species deficit and contribution to species deficit within the pollination mutualism as well as contribution to species deficit within mutualist status to include interactions with distance, area, and precipitation (removed in final model if non-significant).Models are run for dataset in which extremes were constrained to 0 or 1 ("constrained response model", reported in main models, A.), or where extremes were kept ("extreme response model", B.). 4 | Model results for proportional specific deficit and contribution to species deficit for mycorrhizal mutualisms.

SI Table
Model results for GLMs testing drivers of proportional species deficit and contribution to species deficit within the mycorrhizal mutualism as well as contribution to species deficit within mutualist status to include interactions with distance, area, and precipitation (removed in final model if non-significant).Models are run for dataset in which extremes were constrained to 0 or 1 ("constrained response model", reported in main models, A.), or where extremes were kept ("extreme response model", B.). 5 | Model results for proportional specific deficit and contribution to species deficit for N-fixing mutualism.

Model results for GLMs testing drivers of proportional species deficit and contribution to
species deficit within the N-fixing mutualism as well as contribution to species deficit within mutualist status to include interactions with distance, area, and precipitation (removed in final model if non-significant).Models are run for dataset in which extremes were constrained to 0 or 1 ("constrained response model", reported in main models, A.), or where extremes were kept ("extreme response model", B.).

SI Table 1 | Model results for the latitudinal diversity gradient in plant species on mainlands and islands
Model results for GLMs used to test for the LDG on mainlands and islands using.Statistical analysis used Satterthwaite's approximations for t-test and corresponding p values.The significance of the interaction between land type, in particular between mainlands and oceanic islands, and absolute latitude in (A) confirms that although there is a relationship between absolute latitude and species richness on mainlands, this is weakened on oceanic islands.

assuming a constant proportion of the mainland species are capable of colonizing islands confirms that the island slope is significantly different from this null expectation. A. Mainlands v. Islands (df = 946)
SI Table 2 | Model results for drivers of island species deficitResults for models used to test for drivers of island species deficit, including the influence of abiotic variables and the mutualism filter strength, including model averaging (A) and model selection via testing increasing interactions (B,C).The variable 'mutualism filter strength'represents the proportion of mainland floras associating with any one of the three mutualisms included in our analyses(biotic pollination, arbuscular mycorrhizal, or N-fixing).Statistical analysis used Satterthwaite's approximations for t-test and corresponding p values.

Table 3 | Model results for proportional specific deficit and contribution to species deficit for pollination mutualisms
Model results for GLMs testing drivers of proportional species deficit and contribution to species deficit within the pollination mutualism as well as contribution to species deficit within mutualist status to include interactions with distance, area, and precipitation (removed in final model if non-significant).Models are run for dataset in which extremes were constrained to 0 or 1 ("constrained response model", reported in main models, A.), or where extremes were kept ("extreme response model", B.).Statistical analysis used Satterthwaite's approximations for ttest and corresponding p values.A.