Two for one: Partitioning CO2 fluxes and understanding the relationship between solar-induced chlorophyll fluorescence and gross primary productivity using machine learning
Two for one: Partitioning CO2 fluxes and understanding the relationship between solar-induced chlorophyll fluorescence and gross primary productivity using machine learning
复制标题
DOI：
10.1016/j.agrformet.2022.108980
复制
发表时间：
2022-06
影响因子：
6.2
通讯作者：
Weiwei Zhan;Xi Yang;Youn-Mi Ryu;B. Dechant;Yu Huang;Y. Goulas;Minseok Kang;P. Gentine
中科院分区：
文献类型：
--
作者：
Weiwei Zhan;Xi Yang;Youn-Mi Ryu;B. Dechant;Yu Huang;Y. Goulas;Minseok Kang;P. Gentine
准确地将净生态系统交换(NEE)划分为生态系统呼吸(ER)和总初级生产力(GPP)是理解陆地碳循环的关键。标准的划分方法依赖于简化的经验模型，这种模型存在固有的结构性误差。这些结构性错误导致GPP和ER估计有偏差，特别是在极端事件(如干旱)和人为干扰(如作物收成)期间。最近，太阳诱导的叶绿素荧光(SIF)被证明与GPP有很好的相关性，从而提供了一条通过限制GPP来改善NEE分配的途径。然而，GPP和SIF之间的生态系统规模关系仍然有限。在这里，我们表明，由SIF观测通知的神经网络(NNSIF)可以成功地用于划分需求，同时学习生态系统规模的GPP-SIF关系。使用来自不同生态系统的田间数据和由荧光-光合作用耦合模型(SCOPE)产生的合成数据，将NNSIF与标准划分方法和无SIF约束的NN(NNnoSIF)进行了比较。NNSIF表现出以下优势：(1)它有效地改进了ER估计，特别是在高温下；(2)它更好地捕捉到ER上的水分限制；(3)它更准确地估计了LUE对胁迫的变化；(4)它唯一地捕捉到了土地管理(收获)后GPP的快速下降。此外，NNSIF可以在生态系统尺度上反演GPP-SIF关系，并阐明这种关系是如何响应环境条件的。总体而言，我们的算法首次提供了生态系统尺度GPP-SIF关系的直接和非经验估计，而不依赖于任何先前关于CO2通量、气候驱动因素和SIF之间关系的经验假设。NNSIF学到的新知识可以帮助利用卫星SIF更好地估计全球规模的GPP，特别是在极端事件期间和在存在土地管理的情况下。
Accurately partitioning net ecosystem exchange (NEE) into ecosystem respiration (ER) and gross primary productivity (GPP) is critical for understanding the terrestrial carbon cycle. The standard partitioning methods rely on simplified empirical models, which have inherent structural errors. These structural errors lead to biased GPP and ER estimation, especially during extreme events (e.g., drought) and human disturbances (e.g., crop harvest). Recently, solar-induced chlorophyll fluorescence (SIF) has been shown to be well correlated to GPP, thus offering a path to improve the NEE partitioning by constraining GPP. However, the ecosystem-scale relationship between GPP and SIF remains limited. Here, we show that neural networks informed by SIF observations (NNSIF) can be successfully used to partition NEE, while simultaneously learning the ecosystem-scale GPP-SIF relationship. NNSIFwas compared against standard partitioning methods and NN without SIF constraint (NNnoSIF), using field data from different ecosystems and synthetic data generated by a coupled fluorescence-photosynthesis model (SCOPE). NNSIFshowed superior performance as: (1) it effectively improves the ER estimation, especially at high temperature, (2) it better captures the moisture limitation on ER, (3) it more accurately estimates LUE variations to stress, and (4) it uniquely captures the rapid GPP drop after land management (harvest). Furthermore, NNSIFcan retrieve the GPP-SIF relationship at the ecosystem scale, and elucidate how this relationship responds to environmental conditions. Overall, our algorithm provides the first direct and non-empirical estimate of the ecosystem-scale GPP-SIF relationship, without relying on any prior empirical assumptions on the relationships between CO2fluxes, climatic drivers, and SIF. The new knowledge learned by NNSIFcan help better estimate global-scale GPP using satellite SIF, especially during extreme events and in the presence of land management.