The eddy covariance (EC) technique is used to measure the net ecosystem exchange (NEE) of CO₂ between ecosystems and the atmosphere, offering a unique opportunity to study ecosystem responses to climate change. NEE is the difference between the total CO₂ release due to all respiration processes (RECO), and the gross carbon uptake by photosynthesis (GPP). These two gross CO₂ fluxes are derived from EC measurements by applying partitioning methods that rely on physiologically based functional relationships with a limited number of environmental drivers. However, the partitioning methods applied in the global FLUXNET network of EC observations do not account for the multiple co‐acting factors that modulate GPP and RECO flux dynamics. To overcome this limitation, we developed a hybrid data‐driven approach based on combined neural networks (NN_C‐part). NN_C‐part incorporates process knowledge by introducing a photosynthetic response based on the light‐use efficiency (LUE) concept, and uses a comprehensive dataset of soil and micrometeorological variables as fluxes drivers. We applied the method to 36 sites from the FLUXNET2015 dataset and found a high consistency in the results with those derived from other standard partitioning methods for both GPP (R ² > .94) and RECO (R ² > .8). High consistency was also found for (a) the diurnal and seasonal patterns of fluxes and (b) the ecosystem functional responses. NN_C‐part performed more realistic than the traditional methods for predicting additional patterns of gross CO₂ fluxes, such as: (a) the GPP response to VPD, (b) direct effects of air temperature on GPP dynamics, (c) hysteresis in the diel cycle of gross CO₂ fluxes, (d) the sensitivity of LUE to the diffuse to direct radiation ratio, and (e) the post rain respiration pulse after a long dry period. In conclusion, NN_C‐part is a valid data‐driven approach to provide GPP and RECO estimates and complementary to the existing partitioning methods.

中文翻译：

---

使用神经网络将净二氧化碳通量划分为光合作用和呼吸作用。

涡度协方差 (EC) 技术用于测量生态系统与大气之间 CO ₂的净生态系统交换 (NEE) ，为研究生态系统对气候变化的响应提供了独特的机会。NEE 是由于所有呼吸过程 (RECO) 产生的总 CO ₂释放量与光合作用总碳吸收量 (GPP) 之间的差值。这两个总 CO ₂通量是通过应用依赖于基于生理的功能关系与有限数量的环境驱动因素的分区方法从 EC 测量得出的。然而，在 EC 观测的全球 FLUXNET 网络中应用的分区方法并未考虑调节 GPP 和 RECO 通量动态的多个共同作用因素。为了克服这个限制，我们开发了一种基于组合神经网络（NN _C-part）的混合数据驱动方法。NN _C部分通过引入基于光利用效率 (LUE) 概念的光合响应来整合过程知识，并使用土壤和微气象变量的综合数据集作为通量驱动因素。我们将该方法应用于 FLUXNET2015 数据集中的 36 个站点，发现结果与 GPP ( R ²  > .94) 和 RECO ( R ²  > .8) 的其他标准分区方法得出的结果高度一致。（a）通量的昼夜和季节性模式和（b）生态系统功能响应也发现了高度一致性。NN _{C 部分比预测总 CO 2}附加模式的传统方法更真实通量，例如：(a) GPP 对 VPD 的响应，(b) 气温对 GPP 动力学的直接影响，(c) 总 CO ₂通量的柴油循环中的滞后，(d) LUE 对扩散的敏感性与直接辐射的比率，以及（e）长时间干燥后的雨后呼吸脉冲。总之，NN _{C 部分}是一种有效的数据驱动方法，可提供 GPP 和 RECO 估计并补充现有的分区方法。