Abstract It is critical to have long-term carbon dioxide (CO2) flux observations in forest ecosystems to understand how changing climate can affect forest carbon (C) stocks and CO2 exchange between forests and the atmosphere. In this study, fifteen years (2002–2016) of continuous eddy-covariance flux and climate measurements in an intermediate-aged Douglas-fir stand on the east coast of Vancouver Island, Canada, were analyzed. First, the eddy covariance-measured CO2 fluxes were partitioned into gross primary production and ecosystem respiration using two artificial neural networks. Second, the responses of net ecosystem production, gross primary production and ecosystem respiration to interannual climate variability, including five El Nino-Southern Oscillation events, were determined. Three hyper-parameters (number of layers, hidden units, and batch size) of each artificial neural network were set by Bayesian optimization using sequential model-based optimization while the remaining hyper-parameters were taken from the literature. The first artificial neural network was fitted using only nighttime CO2 flux data and applied to estimate nighttime and daytime ecosystem respiration values, and the second one was used to gap-fill gross primary production values. In addition, a predictor analysis was done to investigate the most influential predictors (i.e., environmental variables) within seasons and years. When applied to half-hourly data, the ecosystem respiration model had an R2 of 0.43, whereas the gross primary production model had an R2 of 0.80. The stand was a moderate C sink (average net ecosystem production of 118 ± 404 g C m−2 year−1) during the entire study period, except for the years 2002–2006 when the stand was a moderate C source. The mean annual values of gross primary production and ecosystem respiration were 1649 ± 157 g C m−2 year−1 and 1531 ± 312 g C m−2 year−1, respectively. Our analysis showed that soil temperature was the most important predictor for the ecosystem respiration model, and photosynthetically active irradiance was the most important predictor for the gross primary production model. However, during dry periods in late summer, soil moisture became the most important predictor. Interannual variability of net ecosystem production was only slightly affected by annual total precipitation, mean soil temperature and mean air temperature. Instead, it depended on spring mean air temperature (start of the growing season), summer total precipitation (indicative of water deficiency) and mean summer air temperature. El Nino and La Nina events generally resulted in lower and higher annual net ecosystem production, respectively.

中文翻译：

---

控制花旗松林与大气之间长期二氧化碳交换的因素使用人工神经网络方法确定

摘要 对森林生态系统中的长期二氧化碳 (CO2) 通量进行观测以了解气候变化如何影响森林碳 (C) 储量以及森林与大气之间的二氧化碳交换至关重要。在这项研究中，分析了加拿大温哥华岛东海岸一个中龄花旗松林十五年（2002-2016 年）的连续涡流协方差通量和气候测量。首先，使用两个人工神经网络将涡度协方差测量的 CO2 通量划分为总初级生产和生态系统呼吸。其次，确定了净生态系统生产、初级生产总值和生态系统呼吸对年际气候变率（包括五个厄尔尼诺-南方涛动事件）的响应。三个超参数（层数、隐藏单元、每个人工神经网络的（和批量大小）是通过贝叶斯优化使用基于序列模型的优化来设置的，而其余的超参数取自文献。第一个人工神经网络仅使用夜间 CO2 通量数据进行拟合，并应用于估计夜间和白天生态系统呼吸值，第二个用于填补初级生产总值的缺口。此外，还进行了预测因子分析以调查季节和年份中最具影响力的预测因子（即环境变量）。当应用于半小时数据时，生态系统呼吸模型的 R2 为 0.43，而总初级生产模型的 R2 为 0.80。在整个研究期间，该林分是中等碳汇（平均净生态系统产量为 118 ± 404 g C m−2 year−1），除了 2002 年至 2006 年，当支架是中等碳源时。初级生产总值和生态系统呼吸的年均值分别为 1649 ± 157 g C m−2 year−1 和 1531 ± 312 g C m−2 year−1。我们的分析表明，土壤温度是生态系统呼吸模型最重要的预测因子，而光合活性辐照度是总初级生产模型的最重要预测因子。然而，在夏末干旱时期，土壤水分成为最重要的预测因子。净生态系统产量的年际变化仅受年总降水量、平均土壤温度和平均气温的轻微影响。相反，它取决于春季平均气温（生长季节的开始），夏季总降水量（表明缺水）和夏季平均气温。厄尔尼诺和拉尼娜事件通常分别导致较低和较高的年度净生态系统产量。