Research Highlights

Marine shallow cumulus clouds cool the Earth by reflecting solar radiation back to space and are challenging to accurately represent in earth system models. These clouds are intimately coupled with turbulence in the boundary layer. Here, vertical air motion and its co-variability with cumulus cloudiness are characterized using data from the Atmospheric Radiation Measurement (ARM) Eastern North Atlantic (ENA) observatory.

The Aerosol-Cloud-Drizzle Convection Chamber (ACDC2) collaboration has developed a comprehensive concept and modeling hierarchy for a convection-cloud chamber facility designed to investigate the chain of events from aerosol activation to cloud droplet growth and drizzle formation within turbulent clouds. The proposed 9-meter-tall chamber enables steady-state turbulence and microphysical conditions, facilitating continuous direct observation of cloud and aerosol properties.

This paired study presents a comprehensive investigation of convective boundary layer (CBL) dynamics by integrating four years of high-resolution Doppler lidar observations from five Atmospheric Radiation Measurement (ARM) User Facility Southern Great Plains (SGP) sites with advanced thermodynamics-guided machine learning.The observational analysis (Fig. 1) first quantified significant sub-grid scale heterogeneity—despite relatively flat terrain, daily maximum mixing layer height (MLH) varied by up to 1-km (∼30% of the mean) within a 100-km domain. The 4-year weekly composite diurnal–seasonal MLHs (Fig. 1c–f) revealed a pronounced east–west contrast that reverses seasonally, driven by land-surface gradients. Rigorous statistical analysis further demonstrated that MLH is positively correlated with surface-sensible heat flux (SHF) and negatively correlated with lower tropospheric stability (LTS). However, these traditional correlations could not fully explain the observed site-to-site differences.Building upon these findings, the team developed a novel thermodynamics-guided machine learning framework to overcome the limitations of conventional statistics. By incorporating physics-informed energy-balance constraints and the full diurnal cycle as input features, AutoML (TPOT + AutoKeras) was used to identify the optimal model architecture and parameters. The resulting models achieved high-predictive accuracy (R² = 0.84 at the Central Facility; R² = 0.79–0.81 when transferred to nearby sites). SHAP (SHapley Additive exPlanations) interpretability analysis (Fig. 2) then revealed that LTS remains the dominant predictor year-round, with modest seasonal shifts in feature importance (<10%) and notably higher model uncertainty in summer (JJA), reflecting greater surface-atmospheric interference.