Qiu Ji-Li, Zhang Mi, Pu Yi-Ni, Zhang Zhen, Jia Lei, Zhao Jia-Yu, Xiao Wei, Liu Shou-Dong
Yale-NUIST Center on Atmospheric Environment, Nanjing University of Information Science & Technology, Nanjing 210044, China.
Jiangning District Meteorological Bureau, Nanjing 211100, China.
Ying Yong Sheng Tai Xue Bao. 2022 Oct;33(10):2785-2795. doi: 10.13287/j.1001-9332.202210.021.
Eddy covariance method has become a key technique to measure CH flux continuously in lakes. A large number of CH flux data was missing due to variable reasons. In order to reconstruct a complete time series of CH flux, it is necessary to find an appropriate gap-filling method to insert the CH flux data gap. Based on the routine meteorological data and CH flux data measured at Bifenggang site in the eastern part of the Taihu eddy flux network during 2014 to 2017, we analyzed the control factors of CH flux at the half-hour scale and daily scale. With those data, we tested that whether nonlinear regression method and two machine learning methods, random forest algorithm and error back propagation algorithm, could fill the CH flux gap at the half-hour scale and daily scale. The results showed that CH flux at the half-hour scale was mainly influenced by sediment temperature, friction velocity, air temperature, relative humidity, latent heat flux and water temperature at 20 cm in the growing season, and was mainly affected by relative humidity, latent heat flux, wind speed, sensible heat flux and sediment temperature in non-growing season. The CH flux at the daily scale was mainly affected by latent heat flux and relative humidity. Random forest model was the best in CH flux data gap filling at both time scales. The random forest model with the input variables of day of year, solar elevation angle, sediment temperature, friction velocity, air temperature, water temperature at 20 cm, relative humidity, air pressure, and wind speed was more suitable for filling the CH flux data gap at the half-hour scale. The random forest model with the input variables of day of year, sediment temperature, friction velocity, air temperature, water temperature at 20 cm, relative humidity, air pressure, wind speed, and downward shortwave radiation was more suitable for filling CH flux data gap at the day scale. The interpolation models could fill the data gap better at daily scale than that at the half-hour scale.
涡度相关法已成为湖泊中连续测量CH通量的关键技术。由于各种原因，大量的CH通量数据缺失。为了重建完整的CH通量时间序列，有必要找到合适的插补方法来填补CH通量数据的缺口。基于2014年至2017年太湖涡度通量网络东部碧风港站点实测的常规气象数据和CH通量数据，我们在半小时尺度和日尺度上分析了CH通量的控制因素。利用这些数据，我们测试了非线性回归方法以及两种机器学习方法——随机森林算法和误差反向传播算法——是否能够填补半小时尺度和日尺度上的CH通量缺口。结果表明，在生长季，半小时尺度的CH通量主要受沉积物温度、摩擦速度、气温、相对湿度、潜热通量和20厘米深处水温的影响；在非生长季，主要受相对湿度、潜热通量、风速、感热通量和沉积物温度的影响。日尺度的CH通量主要受潜热通量和相对湿度的影响。在两个时间尺度上，随机森林模型在CH通量数据缺口填补方面表现最佳。输入变量为一年中的日期、太阳高度角、沉积物温度、摩擦速度、气温、20厘米深处水温、相对湿度、气压和风速的随机森林模型更适合填补半小时尺度的CH通量数据缺口。输入变量为一年中的日期、沉积物温度、摩擦速度、气温、20厘米深处水温、相对湿度、气压、风速和向下短波辐射的随机森林模型更适合填补日尺度的CH通量数据缺口。与半小时尺度相比，插值模型在日尺度上能更好地填补数据缺口。
