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 similar to 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: R-2 = 0.66 similar to 0.71, normal: R-2 = 0.78 similar to 0.81; extreme dryness: R-2 = 0.14 similar to 0.30, normal: R-2 = 0.54 similar to 0.55), but the impact on forest is less (extreme heat: R-2 = 0.50 similar to 0.78, normal: R-2 = 0.59 similar to 0.87; extreme dryness: R-2 = 0.86 similar to 0.90, normal: R-2 = 0.81 similar to 0.85). Extreme wet condition did not change model performance in forest ecosystems (with R-2 changing -0.03 similar to 0.03 compared with normal) but led to substantial reduction in model performance in cropland (with R-2 decreasing 0.20 similar to 0.27 compared with normal). Extreme cold condition did not lead to much changes in model performance in forest and woody savannas (with R-2 decreasing 0.01 similar to 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.

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 similar to 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: R-2 = 0.66 similar to 0.71, normal: R-2 = 0.78 similar to 0.81; extreme dryness: R-2 = 0.14 similar to 0.30, normal: R-2 = 0.54 similar to 0.55), but the impact on forest is less (extreme heat: R-2 = 0.50 similar to 0.78, normal: R-2 = 0.59 similar to 0.87; extreme dryness: R-2 = 0.86 similar to 0.90, normal: R-2 = 0.81 similar to 0.85). Extreme wet condition did not change model performance in forest ecosystems (with R-2 changing -0.03 similar to 0.03 compared with normal) but led to substantial reduction in model performance in cropland (with R-2 decreasing 0.20 similar to 0.27 compared with normal). Extreme cold condition did not lead to much changes in model performance in forest and woody savannas (with R-2 decreasing 0.01 similar to 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.