Predicting carbon dioxide and energy fluxes across global FLUXNET sites with regression algorithms
Predicting carbon dioxide and energy fluxes across global FLUXNET sites with regression algorithms
复制标题
DOI：
10.5194/bg-13-4291-2016
复制
发表时间：
2016-01-01
期刊：
影响因子：
4.9
通讯作者：
Papale, Dario
中科院分区：
文献类型：
--
作者：
Tramontana, Gianluca;Jung, Martin;Papale, Dario
从数据驱动模式导出的陆-气通量时空场可以补充基于过程的陆面模式的模拟。虽然已经应用了许多具有涡度协方差通量数据的经验模型策略，但迄今为止尚未对这些方法进行系统的相互比较。在这项研究中，我们进行了交叉验证实验，用于预测不同生态系统类型的二氧化碳，潜热，显热和净辐射通量，使用来自四个不同类别的11种机器学习（ML）方法（核方法，神经网络，树方法和回归样条）。我们应用了两个互补的设置：（1）8天的平均通量的基础上遥感数据和（2）每日平均通量的基础上气象数据和平均季节周期的遥感变量。来自不同ML和实验设置的预测模式高度一致。各通量表现出系统性差异，由大到小依次为：生态系统净交换（R-2 < 0.5）、生态系统呼吸（R-2 > 0.6）、初级生产总值（R-2 > 0.7）、潜热（R-2> 0.7）、感热（R-2 > 0.7）和净辐射（R-2 > 0.8）。最大似然法对观测通量的跨站点变化和平均季节周期的预测效果很好（R2> 0.7），但对8天的平均季节周期偏差的预测效果不好（R-2 < 0.5）。通量在森林和温带气候站点比在极端气候或训练数据较少代表的站点更好地预测（例如，热带）。经评估的基于ML的模型的大型集合将成为新的全球通量产品的基础。
Spatio-temporal fields of land-atmosphere fluxes derived from data-driven models can complement simulations by process-based land surface models. While a number of strategies for empirical models with eddy-covariance flux data have been applied, a systematic intercomparison of these methods has been missing so far. In this study, we performed a cross-validation experiment for predicting carbon dioxide, latent heat, sensible heat and net radiation fluxes across different ecosystem types with 11 machine learning (ML) methods from four different classes (kernel methods, neural networks, tree methods, and regression splines). We applied two complementary setups: (1) 8-day average fluxes based on remotely sensed data and (2) daily mean fluxes based on meteorological data and a mean seasonal cycle of remotely sensed variables. The patterns of predictions from different ML and experimental setups were highly consistent. There were systematic differences in performance among the fluxes, with the following ascending order: net ecosystem exchange (R-2 < 0.5), ecosystem respiration (R-2 > 0.6), gross primary production (R-2 > 0.7), latent heat (R-2 > 0.7), sensible heat (R-2 > 0.7), and net radiation (R-2 > 0.8). The ML methods predicted the across-site variability and the mean seasonal cycle of the observed fluxes very well (R 2 > 0.7), while the 8-day deviations from the mean seasonal cycle were not well predicted (R-2 < 0.5). Fluxes were better predicted at forested and temperate climate sites than at sites in extreme climates or less represented by training data (e.g., the tropics). The evaluated large ensemble of ML-based models will be the basis of new global flux products.