How soil microbes assimilate carbon-C, nitrogen-N, phosphorus-P and sulfur-S is fundamental for understanding nutrient cycling in terrestrial ecosystems. We compiled a global database of C, N, P and S concentrations in soils and microbes and developed relationships between them by using a power function model. The C:N:P:S was estimated to be 287:17:1:0.8 for soils and 42:6:1:0.4 for microbes. We found a convergence of the relationships between elements in soils and in soil microbial biomass across C, N, P and S. The element concentrations in soil microbial biomass follow a homeostatic regulation curve with soil element concentrations across C, N, P and S, implying a unifying mechanism of microbial assimilating soil elements. This correlation explains the well-constrained C:N:P:S stoichiometry with a slightly larger variation in soils than in microbial biomass. Meanwhile, it is estimated that the minimum requirements of soil elements for soil microbes are 0.8 mmol C Kg⁻¹ dry soil, 0.1 mmol N Kg⁻¹ dry soil, 0.1 mmol P Kg⁻¹ dry soil and 0.1 mmol S Kg⁻¹ dry soil, respectively. These findings provide a mathematical explanation of element imbalance in soils and soil microbial biomass and offer insights for incorporating microbial contribution to nutrient cycling into Earth system models.

The net ecosystem CO₂ exchange (NEE) is a critical parameter for quantifying terrestrial ecosystems and their contributions to the ongoing climate change. The accumulation of ecological data is calling for more advanced quantitative approaches for assisting NEE prediction. In this study, we applied two widely used machine learning algorithms, Random Forest (RF) and Extreme Gradient Boosting (XGBoost), to build models for simulating NEE in major biomes based on the FLUXNET dataset. Both models accurately predicted NEE in all biomes, while XGBoost had higher computational efficiency (6~62 times faster than RF). Among environmental variables, net solar radiation, soil water content, and soil temperature are the most important variables, while precipitation and wind speed are less important variables in simulating temporal variations of site-level NEE as shown by both models. Both models perform consistently well for extreme climate conditions. Extreme heat and dryness led to much worse model performance in grassland (extreme heat: R² = 0.66~0.71, normal: R² = 0.78~0.81; extreme dryness: R² = 0.14~0.30, normal: R² = 0.54~0.55), but the impact on forest is less (extreme heat: R² = 0.50~0.78, normal: R² = 0.59~0.87; extreme dryness: R² = 0.86~0.90, normal: R² = 0.81~0.85). Extreme wet condition did not change model performance in forest ecosystems (with R² changing −0.03~0.03 compared with normal) but led to substantial reduction in model performance in cropland (with R² decreasing 0.20~0.27 compared with normal). Extreme cold condition did not lead to much changes in model performance in forest and woody savannas (with R² decreasing 0.01~0.08 and 0.09 compared with normal, respectively). Our study showed that both models need training samples at daily timesteps of >2.5 years to reach a good model performance and >5.4 years of daily samples to reach an optimal model performance. In summary, both RF and XGBoost are applicable machine learning algorithms for predicting ecosystem NEE, and XGBoost algorithm is more feasible than RF in terms of accuracy and efficiency.