Machine learning significantly improves the simulation of hourly-to-yearly scale cloud nuclei concentration and radiative forcing in polluted atmosphere

This study used an efficient machine learning method (Random Forest) to construct a new framework of CCN prediction by combining multi-source dataset and the CCN concentration simulated by the Weather Research and Forecasting coupled with Chemistry (WRF-Chem) model, which predicts well both regional and hourly-to-yearly scale CCN concentration at typical supersaturations in the North China Plain. The dataset is provided in csv format.