Stable gap-filling for longer eddy covariance data gaps: A globally validated machine-learning approach for carbon dioxide, water, and energy fluxes

• A gap-filling technique (RFR) was proposed to fill long gaps for eddy covariance. • Validated at 94 sites globally, RFR outperformed the research standard method. • RFR performed stably in longer gaps (one month long continuous gaps). Continuous time-series of CO 2 , water, and energy fluxes are useful for evaluating the impacts of climate-change and management on ecosystems. The eddy covariance (EC) technique can provide continuous, direct measurements of ecosystem fluxes, but to achieve this gaps in data must be filled. Research-standard methods of gap-filling fluxes have tended to focus on CO 2 fluxes in temperate forests and relatively short gaps of less than two weeks. A gap-filling method applicable to other fluxes and capable of filling longer gaps is needed. To address this challenge, we propose a novel gap-filling approach, Random Forest Robust (RFR). RFR can accommodate a wide range of data gap sizes, multiple flux types (i.e. CO 2 , water and energy fluxes). We configured RFR using either three (RFR 3 ) or ten (RFR 10 ) driving variables. RFR was tested globally on fluxes of CO 2 , latent heat (LE), and sensible heat (H) from 94 suitable FLUXNET2015 sites by using artificial gaps (from 1 to 30 days in length) and benchmarked against the standard marginal distribution sampling (MDS) method. In general, RFR improved on MDS's R 2 by 15% (RFR 3 ) and by 30% (RFR 10 ) and reduced uncertainty by 70%. RFR's improvements in R 2 for H and LE were more than twice the improvement observed for CO 2 fluxes. Unlike MDS, RFR performed well for longer gaps; for example, the R 2 of RFR methods in filling 30-day gaps dropped less than 4% relative to 1-day gaps, while the R 2 of MDS dropped by 21%. Our results indicate that the RFR method can provide improved gap-filling of CO 2 , H and LE flux timeseries. Such improved continuous flux measurements, with low bias, can enhance our understanding of the impacts of climate-change and management on ecosystems globally.