Predicting Atmospheric Particle Phase State Using an Explainable Machine Learning Approach Based on Particle Rebound Measurements.

Abstract

The particle phase state plays a vital role in the gas-particle partitioning, multiphase reactions, ice nucleation activity, and particle growth in the atmosphere. However, the characterization of the atmospheric phase state remains challenging. Herein, based on measured aerosol chemical composition and ambient relative humidity (RH), a machine learning (ML) model with high accuracy (R2 = 0.952) and robustness (RMSE = 0.078) was developed to predict the particle rebound fraction, f, which is an indicator of the particle phase state. Using this ML model, the f of particles in the urban atmosphere was predicted based on seasonal average aerosol chemical composition and RH. Regardless of seasons, aerosols remain in the liquid state of mid-high latitude cities in the northern hemisphere and in the semisolid state over semiarid regions. In the East Asian megacities, the particles remain in the liquid state in spring and summer and in the semisolid state in other seasons. The effects of nitrate, which is becoming dominant in fine particles in several urban areas, on the particle phase state were evaluated. More nitrate led the particles to remain in the liquid state at an even lower RH. This study proposed a new approach to predict the particle phase state in the atmosphere based on RH and aerosol chemical composition.