Cloud condensation nuclei (CCN) are mediators of aerosol–cloud interactions, which contribute to the largest uncertainty in climate change prediction. Here, we present a machine learning/artificial intelligence model that quantifies CCN from variables of aerosol composition, atmospheric trace gases, and meteorology. Comprehensive multi-campaign airborne measurements, covering varied physicochemical regimes in the troposphere, confirm the validity of and help probe the inner workings of this machine learning model: revealing for the first time that different ranges of atmospheric aerosol composition and mass correspond to distinct aerosol number size distributions. Machine learning extracts this information, important for accurate quantification of CCN, additionally from both chemistry and meteorology. This can provide a physicochemically explainable, computationally efficient, robust machine learning pathway in global climate models that only resolve aerosol composition; potentially mitigating the uncertainty of effective radiative forcing due to aerosol–cloud interactions (ERFaci) and improving confidence in assessment of anthropogenic contributions and climate change projections.