Global high-resolution ultrafine particle number concentrations through data fusion with machine learning presents the first global maps of particle number concentration (PNC) and associated ultrafine particles (UFPs) at 1 km resolution over land for 2010–2019, led by the Climate and Atmosphere Research Center (CARE-C) of The Cyprus Institute in close collaboration with the Computation-based Science and Technology Research Center (CaSToRC) of The Cyprus Institute and the Max Planck Institute for Chemistry (MPIC). The study fuses long-term measurements from 155 ground stations with a rich set of global predictors, including emissions, NO₂ and PM₂.₅ fields, population and built-up volume, road networks, and key meteorological variables, using an XGBoost regression model with conformal prediction for uncertainty quantification. The model attains R²≈0.90 on an independent test set and R² of 0.77–0.87 under spatial and temporal cross‑validation, and indicates that UFPs constitute on average about 91% of total PNC, with annual mean near-surface PNC ranging from a few thousand cm⁻³ in pristine regions to over 40,000 cm⁻³ in polluted urban centres. The resulting open-access NetCDF dataset (2010–2019) provides annual mean PNC, UFP and 95% coverage intervals on a global 1 km grid, enabling direct integration with high‑resolution population data for exposure and health impact studies.