Global soil methane uptake inferred from global field measurements

Soil methane (CH₄) uptake is an important sink in the global methane budget. However, both the magnitude and the dynamics of global soil CH₄ uptake remain highly uncertain. Here, by compiling an extensive data set of 6899 site-months of soil CH₄ fluxes observed at 682 sites, we use a machine-learning algorithm (Random Forest) to provide a data-driven estimate of global soil CH₄ uptake each month from 1981 to 2018. Varying the combination of predictors, we construct 9 different simulations for three landcover types (Forests, Grasslands, Croplands). The dataset uploaded is the mean of 9 simulations after calculating the area-weighted average of CH₄flux of three landcover types.