A 21-year global dataset of particle number concentrations (N100 and N50) for aerosol-cloud interaction studies

This dataset contains global ground‑level particle number concentrations for the period 2003--2024. It includes two variables: the number concentrations for particles with dry diameters larger than 100 nm (N100) and larger than 50 nm (N50). The variables are provided at 0.75x0.75 degree spatial resolution and daily temporal resolution for the entire time period. The dataset was generated using an eXtreme Gradient Boosting (XGBoost) model, trained with measurements from 62 in situ stations, and global reanalysis variable fields. This approach enabled a data-driven representation of particle number concentrations at the global scale. The details about the method can be found in "A 21-year global dataset of particle number concentrations for aerosol-cloud interaction studies" by Ovaska et al. (2026). The dataset is organised in yearly NetCDF-files. The variables in the files are: time Time coordinate of the dataset (UTC), beginning of the averaging period. latitude Latitude coordinate in degrees north. longitude Longitude coordinate in degrees east. N100 Modelled daily-averaged number concentration of particles larger than 100 nm (cm⁻³).Produced using an XGBoost-based model following Ovaska et al. (2026). N50 Modelled daily-averaged number concentration of particles larger than 50 nm (cm⁻³).Produced using an XGBoost-based model following Ovaska et al. (2026).