Abstract
Five machine learning (ML) algorithms were employed for gap-filling surface fluxes of CO2, water vapor, and sensible heat above three different ecosystems: grassland, rice paddy field, and forest. The performance and limitations of these ML models, which are support vector machine, random forest, multi-layer perception, deep neural network, and long short-term memory, were investigated. Firstly, the accuracy of gap-filling to time and hysteresis input factors of ML algorithms for different ecosystems is discussed. Secondly, the optimal ML model selected in the first stage is compared with the classic method—the Penman–Monteith (P–M) equation for water vapor flux gap-filling. Thirdly, with different gap lengths (from one hour to one week), we explored the data length required for an ML model to perform the optimal gap-filling. Our results demonstrate the following: (1) for ecosystems with a strong hysteresis between surface fluxes and net radiation, adding proceeding meteorological data into the model inputs could improve the model performance; (2) the five ML models gave similar gap-filling performance; (3) for gap-filling water vapor flux, the ML model is better than the P–M equation; and (4) for a gap with length of half day, one day, or one week, an ML model with training data length greater than 1300 h would provide a better gap-filling accuracy.
Highlights
In order to study climate change, hydrological cycle, and atmosphere–surface interactions, information on fundamental factors such as carbon dioxide (CO2 ), latent heat (LE), and sensible heat (H) fluxes are indispensable
For the grassland site, the hysteresis factors played no roles in all three fluxes, and the time factors have some influences on all fluxes at the three sites
To further examine the influences of time factors and hysteresis factors on the three fluxes at the three sites, the averaged model performances with and without these two factors are summarized in Tables 5–7 for the grassland, rice paddy field, and forest, respectively
Summary
In order to study climate change, hydrological cycle, and atmosphere–surface interactions, information on fundamental factors such as carbon dioxide (CO2 ), latent heat (LE), and sensible heat (H) fluxes are indispensable. The most accurate and reliable method to obtain these surface flux data is the eddy-covariance method. This method relies on high frequency measurements of three-dimensional sonic anemometers and CO2 /H2 O infrared gas analyzers, which are often forced to stop by rain or instrument maintenance, and complete flux time series data sometimes cannot be obtained. The process of data quality inspection will result in missing flux data. Gap-filling missing flux data is a key process for calculating mass and energy budgets, such as ecological carbon budgets, evapotranspiration, and water resource balance. Used gap-filling methods adopt low-frequency meteorological information such as temperature, humidity, wind speed, and net radiation to perform linear or non-linear regressions to make up loss data
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
