Gap-filling eddy covariance methane fluxes: Comparison of machine learning model predictions and uncertainties at FLUXNET-CH4 wetlands
Gap-filling eddy covariance methane fluxes: Comparison of machine learning model predictions and uncertainties at FLUXNET-CH4 wetlands
复制标题
DOI：
10.1016/j.agrformet.2021.108528
复制
发表时间：
2021-07-10
影响因子：
6.2
通讯作者：
Jackson, Robert B.
中科院分区：
文献类型：
--
作者：
Irvin, Jeremy;Zhou, Sharon;Jackson, Robert B.
时间序列的湿地甲烷通量测量涡度协方差需要填补空白，以估计每日，季节性和年度排放量。填补空白的甲烷通量是具有挑战性的，因为高变异性和复杂的反应，多个驱动程序。到目前为止，没有广泛建立的湿地甲烷通量的填补空白的标准，关于最好的模型算法和预测。本研究综合了不同的间隙填充方法系统地应用于17个湿地网站跨越北方到热带地区，包括所有主要的湿地类和两个稻田的结果。建议的程序用于：1）创建现实的人工间隙情景，2）训练和评估间隙填充模型，而不夸大性能，3）预测半小时甲烷通量和年度排放量与现实的不确定性估计。性能之间的传统方法（边际分布抽样）和四个机器学习算法进行了比较。传统方法实现了与机器学习模型相似的中值性能，但比最好的机器学习模型更差，并且对预测器选择相对不敏感。在机器学习模型中，决策树算法在交叉验证实验中表现最好，即使使用基线预测器集，人工神经网络在使用所有预测器时表现出相当的性能。土壤温度通常是最重要的预测因素，而地下水位深度在地下水位波动较大的地点很重要，这凸显了湿地土壤条件数据的价值。来自机器学习模型的原始间隙填充不确定性被低估了，我们提出了一种方法来校准观测的不确定性。用于模型开发、评估和不确定性估计的Python代码已公开发布。本研究概述了模块化且强大的机器学习工作流程，并为甲烷间隙填充模型提出了建议并评估了改进的基线，这些模型可以在多地点合成或区域和全球通量网络的标准化产品中实施（例如，FLUXNET）。
Time series of wetland methane fluxes measured by eddy covariance require gap-filling to estimate daily, seasonal, and annual emissions. Gap-filling methane fluxes is challenging because of high variability and complex responses to multiple drivers. To date, there is no widely established gap-filling standard for wetland methane fluxes, with regards both to the best model algorithms and predictors. This study synthesizes results of different gap-filling methods systematically applied at 17 wetland sites spanning boreal to tropical regions and including all major wetland classes and two rice paddies. Procedures are proposed for: 1) creating realistic artificial gap scenarios, 2) training and evaluating gap-filling models without overstating performance, and 3) predicting halfhourly methane fluxes and annual emissions with realistic uncertainty estimates. Performance is compared between a conventional method (marginal distribution sampling) and four machine learning algorithms. The conventional method achieved similar median performance as the machine learning models but was worse than the best machine learning models and relatively insensitive to predictor choices. Of the machine learning models, decision tree algorithms performed the best in cross-validation experiments, even with a baseline predictor set, and artificial neural networks showed comparable performance when using all predictors. Soil temperature was frequently the most important predictor whilst water table depth was important at sites with substantial water table fluctuations, highlighting the value of data on wetland soil conditions. Raw gap-filling uncertainties from the machine learning models were underestimated and we propose a method to calibrate uncertainties to observations. The python code for model development, evaluation, and uncertainty estimation is publicly available. This study outlines a modular and robust machine learning workflow and makes recommendations for, and evaluates an improved baseline of, methane gap-filling models that can be implemented in multi-site syntheses or standardized products from regional and global flux networks (e.g., FLUXNET).