Anthropogenic climate change may reduce global diazotroph diversity

Abstract

Climate change impacts microbial community structure and function, thus altering biogeochemical cycles. Biological nitrogen fixation by diazotrophs is involved in maintaining the balance of the global nitrogen cycle, but the global biogeographic patterns of diazotrophs and their responses to climate change remain unclear. In this study, we use a dataset of 1352 potential diazotrophs by leveraging the co-occurrence of nitrogenase genes (nifHDK) and analyse the global distribution of potential diazotrophs derived from 137,672 samples. Using the random forest model, we construct a global map of diazotroph diversity, revealing spatial variations in diversity across large scales. Feature importance shows that precipitation and temperature may act as drivers of diazotroph diversity, as these factors explain 54.2% of the variation in the global distribution of diazotroph diversity. Using projections of future climate under different shared socioeconomic pathways, we show that overall diazotroph diversity could decline by 1.5%-3.3%, with this decline further exacerbated by development patterns that increase carbon emissions. Our findings highlight the importance of sustainable development in preserving diazotrophs.

Fig. 1. Composition and diversity of diazotrophs across microbial taxa.

a UpSet plot illustrating the co-occurrence of nitrogenase-related genes across diverse genomes. The accompanying pie chart depicts the proportional classification of different genome categories. b Phylogenetic tree of representative prokaryotic whole genomes, with branch colours indicating distinct bacterial phyla. The genome classifications are included in the outer rings. c Proportion (%) and number of nitrogen-fixing genomes across different phyla within representative genomes. Source data are provided as a Source Data file.

Fig. 2. Global diversity and biogeography of diazotrophic communities across habitats.

a Latitudinal distribution of diazotroph relative richness in terrestrial and marine ecosystems, with colour variations indicating the mean annual temperature in each sample (terrene: two-sided Pearson correlation test, r(96,989) = −0.061, P = 2.73 × 10⁻⁸⁰, t = −18.993, 95% CI = [−0.067, −0.055]; marine: two-sided Pearson correlation test, r(27,671) = −0.031, P = 2.85 × 10⁻⁷, t = −5.134, 95% CI = [−0.042, −0.019]). b Relative richness of diazotrophic communities across different habitats. The sample numbers are included in the label. c Principal coordinate analysis of diazotrophic community composition across various habitats, with the distance matrix generated using Bray-Curtis dissimilarity. d Proportions of stochastic processes of diazotrophic communities in different habitats. The box plots display the median (middle line) and the 25th (Q1) and 75th (Q3) percentiles (box boundaries), and the whiskers indicate the Q1 − 1.5 IQR and Q3 + 1.5 IQR of the observations. Each box summarizes statistical distributions derived from randomized subsampling iterations (n = 100) per habitat. Blue represents aquatic environments, and yellow indicates soil environments. Source data are provided as a Source Data file.

Fig. 3. Global maps and environmental drivers of the relative richness of diazotrophs.

a Relative richness of terrestrial diazotrophs across the world. Sixty-three covariates (resampled resolution of 0.05°) were used in the final random forest model prediction (training dataset with 10-fold cross-validation R² = 0.558, testing set with R² = 0.519; Supplementary Fig. 3). Pixels with missing values for covariates are indicated by blanks. b Latitudinal variation in the relative richness of diazotrophs. The y-axis represents relative richness, and the colour represents the density of the pixels with close relative richness. c Relative importance of environmental covariates in the random forest model. The names of the environmental covariates are given in abbreviated form (Supplementary Table 2). d Importance of individual environmental covariates in the random forest model. The top three indices are the mean annual precipitation (bio_12), soil pH (phh2o), and aridity index (ai). IncNodePurity, or increase in node purity, is measured by the sum of squared residuals and represents the effect of each variable on the heterogeneity of observations at each node of the classification tree, thus reflecting the importance of the variables. Source data are provided as a Source Data file.

Fig. 4. Decrease in diazotrophic community relative richness under future climate scenarios.

a Trends in the relative richness of diazotrophs under future climate scenarios (2080–2100). The prediction model was based on current bioclimatic variables (resolution of 0.083°) and constructed by the random forest algorithm (Supplementary Fig. 10). The model was used to predict the relative richness of potential future nitrogen-fixing organisms under four climate scenarios for different carbon emission societies (SSP: shared socioeconomic pathway; SSP126: sustainability; SSP245: middle of the road; SSP370: regional rivalry; SSP585: fossil-fuelled development), and we averaged the predictions of downscaled global change models (GCMs; n  =  14 for SSP126; n  =  12 for SSP245 and SSP585; n  =  11 for SSP370) under the same climate scenarios and calculated their changes relative to the current climate (Supplementary Fig. 11). b Overall change in the relative richness of diazotrophs across latitudes under different climate scenarios. We calculated the mean changes in relative richness and showed trends by latitude. c Changes in relative richness across continents under different climate scenarios. We show overall changes in relative richness compared with the current values in all GCMs for each climate scenario based on different intercontinental divisions. For the box plots, the middle line indicates the median, the box represents the 25th (Q1) and 75th (Q3) percentiles (box boundaries), and the whiskers indicate the Q1 − 1.5 IQR and Q3 + 1.5 IQR of the observations. d Proportion of area occupied by each continent whose relative richness changed under different climate scenarios. The bar plot shows the proportions of relative changes in area based on different intercontinental divisions (e.g., the proportions of relative decreases in area are defined as the ratio of the number of pixels in the decreased region to the overall number of pixels). The colour indicates the direction of change for relative richness (increases or decreases). Source data are provided as a Source Data file.