Erosion of global functional diversity across the tree of life

Abstract

Although one-quarter of plant and vertebrate species are threatened with extinction, little is known about the potential effect of extinctions on the global diversity of ecological strategies. Using trait and phylogenetic information for more than 75,000 species of vascular plants, mammals, birds, reptiles, amphibians, and freshwater fish, we characterized the global functional spectra of each of these groups. Mapping extinction risk within these spectra showed that larger species with slower pace of life are universally threatened. Simulated extinction scenarios exposed extensive internal reorganizations in the global functional spectra, which were larger than expected by chance for all groups, and particularly severe for mammals and amphibians. Considering the disproportionate importance of the largest species for ecological processes, our results emphasize the importance of actions to prevent the extinction of the megabiota.

Fig. 1. Global functional spectra.

Global functional spectra of plants (A), mammals (B), birds (C), reptiles (D), amphibians (E), and freshwater fish (F). Probabilistic species distributions in the spaces defined by the two first principal components (PC1 and PC2) of PCA (details in table S3) considering different functional traits for each group (see table S1 for definitions of each functional trait). Arrows indicate the direction and weighting of each trait in the PCA. The color gradient (red, yellow, and white) depicts different density of species in the defined space (red areas are more densely populated). Arrows show the loadings of the considered traits in the resulting PCA. Thick contour lines indicate the 0.5 (hotspots, see main text) and 0.99 quantiles, and thinner ones indicate quantiles 0.6, 0.7, 0.8, and 0.9. Silhouettes were downloaded from PhyloPic (www.phylopic.org). The legends within each panel show the amount of functional space (measured in SD units, SD2, except for freshwater fish, in SD4) occupied by the hotspots (0.5 quantile) and the 0.99 quantile distribution. sla, specific leaf area; ln, nitrogen content per unit leaf mass; sm, seed mass; la, leaf area; ph, plant height; ssd, specific stem density; ls, litter size; svl, snout-vent length; bm, adult body mass; long, longevity; wea, weaning length; fmat, time to reach female maturity; gest, gestation length; em, egg mass; fa, fledging age; inc, incubation time; am, age at maturity; bs, body size; os, offspring size; es, eye size; mp, mouth position; pp, pectoral position; ms, mouth size; elo, body elongation; cs, caudal peduncle throttling; ps, pectoral fin size; wid, lateral body shape.

Fig. 2. Risk of extinction in the functional space.

Extinction risk in the functional spaces of plants (A), mammals (B), birds (C), reptiles (D), amphibians (E), and freshwater fish (F). Probability of species being classified as threatened (see Materials and Methods) according to GAMs (with binomial distribution) using the position of species in the functional space as predictors. Yellow tones indicate lower risk of extinction, whereas purple tones indicate high risk of extinction. Legend shows χ² and P values of the GAM corresponding to each taxonomic group. For each group, the red contour lines indicate the average threat probability (proportion of species classified as threatened in the group). The gray line indicates the 0.99 quantile of the spectra of each group considering only species whose threat status is known.

Fig. 3. Effects of simulated extinction scenarios on different functional diversity indicators of the different taxonomic groups.

Values of functional richness (top row), functional redundancy (central row), and overlap with the current TPD functions (bottom row) of the TPD functions estimated after simulated extinctions (current values of each index are denoted by the value 1 in all plots). The x axis of all figures correspond to different extinction scenarios (total of 101 scenarios with 100 repetitions each), ranging from 50% fewer extinctions than under the central scenario (based on IUCN 100-year extinction probabilities) to 50% more extinctions than under the central scenarios (numbers of extinct species per group in these three cases are shown in the bottom row). Lines represent the fits of GAM (mean ± 2 SE) in which smooth functions of the number of species gone extinct were fitted for both realistic extinctions (based on IUCN categories; orange line) and random extinctions (blue lines). In all cases, the AIC (Akaike information criterion) values of the model including two smooths were much smaller (difference > 10 AIC) than a model including a single smooth for the number of species extinct; hence, the two lines are always represented. sp., species.

Fig. 4. Shifts in the functional spectra after extinctions.

Shifts in functional spectra after simulated extinctions for plants (A), mammals (B), birds (C), reptiles (D), amphibians (E), and freshwater fish (F). Differences (expressed in quantile changes) between the functional spectra of species assessed by IUCN before and after simulated extinctions based on IUCN category–based probabilities of extinction. For each group, the plot represents the average of the TPD functions of the 100 simulations performed for the central scenario of extinctions (see Materials and Methods). Brown tones reflect areas in which the TPD quantiles are lower after extinctions (i.e., those traits become relatively less frequent at the global scale), and blue tones reflect areas in which the TPD quantiles increase (i.e., those traits become relatively more frequent at the global scale). Black areas show the parts of the functional space that would disappear from the global spectra after extinctions (trait combinations that go completely extinct). The legend for each group shows the average absolute change in quantiles across the spectra and the range of these changes. Figure S5 shows similar plots for the two extreme extinction scenarios considered (−50 and +50% extinctions).