The X-BASE products are global fluxes based on the FLUXCOM-X framework which trains machine learning models on in-situ eddy covariance data and uses them to produce these global products. The X-BASE experiment is a basic configuration to serve as a baseline for the FLUXCOM-X framework and includes as predictors the core meteorological data, plant functional type classification as well as MODIS based vegetation indices and land surface temperature. XGBoost was used as the machine learning algorithm. The product is described in Nelson et al., X-BASE: the first terrestrial carbon and water flux products from an extended data-driven scaling framework, FLUXCOM-X, EGUsphere [preprint], https://doi.org/10.5194/egusphere-2024-165, 2024.
The edition of the data provides the global exchange fluxes for CO2 as GPP, NEE, and water vapor as transpiration and evapotranspiration for the years 2001 until 2021. Depending on the spatial resolution of the data the temporal resolutions are:
- 0.5 degree: monthly
- 0.25 degree: daily, monthly diurnal cycle
- 0.05 degree: monthly
