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 (R 2 = 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.

Influence of Relative Humidity and Composition on PM2.5 Phases in Northeast Asia

“…This trend can be attributed to the higher hygroscopicity of inorganic aerosols compared to that of their organic counterparts., ,, When ALWC/PM 2.5 was <∼0.5, a semisolid phase state was predominant (more than 80% of the total PM 2.5 samples, red symbols in Figure ), whereas when ALWC/PM 2.5 was ≥∼0.5, a liquid phase state was predominant (more than 80% of the total PM 2.5 samples, green symbols in Figure ). A recent study of Qiu et al investigated the relationship between ALWC/PM 1.0 and phase states of aerosol particles. The authors showed that PM 1.0 tended to be a liquid phase state in Beijing when ALWC/PM 1.0 >∼0.3.…”

Unlocking the Mystery of Aerosol Phase Transitions Governed by Relative Humidity History Through an Advanced Outdoor Nephelometer System

“…Over the past decade, in China, aerosol phase state has become a focal point in atmospheric aerosol research (Kuang et al, 2016;Y. Liu et al, 2017;Qiu et al, 2023;Sun et al, 2018). These findings collectively suggest that aerosols in ambient air may exist in stable or partially metastable states when the RH of the air is below the critical fully DRH.…”

“…The characteristics of ambient aerosols exhibiting deliquescent behavior, along with the corresponding deliquescence relative humidity (DRH) and efflorescence RH (ERH), are influenced by aerosol chemical composition, including the proportions of nitrate (Sun et al., 2018) and secondary organic aerosols (SOA) (Saukko et al., 2015; Wang et al., 2021), as well as other factors such as mixing state (Li et al., 2021; Xiong et al., 2023). Over the past decade, in China, aerosol phase state has become a focal point in atmospheric aerosol research (Kuang et al., 2016; Y. Liu et al., 2017; Qiu et al., 2023; Sun et al., 2018). These findings collectively suggest that aerosols in ambient air may exist in stable or partially metastable states when the RH of the air is below the critical fully DRH.…”