In recent years, artificial intelligence (AI), as a rapidly developing and powerful tool to solve practical problems, has attracted much attention and has been widely used in various areas. Owing to their strong learning and accurate prediction abilities, all sorts of AI models have also been applied in wastewater treatment (WWT) to optimize the process, predict the efficiency and evaluate the performance, so as to explore more cost-effective solutions to WWT. In this review, we summarize and analyze various AI models and their applications in WWT. Specifically, we briefly introduce the commonly used AI models and their purposes, advantages and disadvantages, and comprehensively review the inputs, outputs, objectives and major findings of particular AI applications in water quality monitoring, laboratory-scale research and process design. Although AI models have gained great success in WWT-related fields, there are some challenges and limitations that hinder the widespread applications of AI models in real WWT, such as low interpretability, poor model reproducibility and big data demand, as well as a lack of physical significance, mechanism explanation, academic transparency and fair comparison. To overcome these hurdles and successfully apply AI models in WWT, we make recommendations and discuss the future directions of AI applications.

Heterogeneous ice nucleation initiated by atmospheric ice-nucleating particles (INPs) is a key microphysical process for cloud formation. Detecting the ice nucleation ability (INA) and concentration of INPs is essential for improving global climate models. Droplet freezing techniques (DFTs) are among the widely used tools for measuring the immersion freezing of INPs, which is a predominant ice nucleation process in mixed-phase clouds. To enhance the efficiency and accuracy of DFTs, we developed a Freezing Ice Nucleation Detection Analyzer at Westlake University (FINDA-WLU) with an improved hardware setup, user-friendly software, precise droplet freezing detection, and rigorous temperature calibrations. The temperature uncertainty of FINDA-WLU is about ±0.60 °C, considering both vertical heat transfer efficiency and horizontal temperature heterogeneity. The system is tested with Milli-Q ultrapure water and reference materials like Arizona Test Dust and Snomax^®, and the results are consistent with previous studies. We also use the FINDA-WLU to measure INPs in precipitation samples collected in China. Overall, FINDA-WLU proved to be a reliable and precise method for measuring INA and INP concentrations.

Marine boundary layer (MBL) clouds exert a strong cooling influence on Earth’s climate, yet their response to aerosol perturbations remains one of the largest uncertainties in climate projections. A key challenge is identifying which aerosol and meteorological factors control cloud droplet number concentration (Nd), especially when boundary-layer structure alters the transport of surface-emitted aerosol to cloud base. Here, we combine aircraft and ground-based measurements from the Aerosol and Cloud Experiments in the Eastern North Atlantic (ACE-ENA) campaign with the aerosol activation parameterization to quantify controlling factors on Nd during different seasons. We found that summer and winter boundary layer decoupling modulates the vertical transport of aerosols within the MBL and thereby influences cloud condensation nuclei number concentration (NCCN) at cloud base. In both seasons, decoupling occurs for roughly 32 % of the total time, during which ~60 % of accumulation-mode and ~75 % of Aitken-mode aerosols fail to reach the cloud layer. The out-of-cloud accumulation-mode particle number concentration (Nacc) is higher in summer than in winter, whereas the corresponding Nd is comparable between the two seasons. Sensitivity experiments show that Nacc is the dominant control on Nd in summer, whereas cloud droplet formation in winter is additionally sensitive to Aitken-mode aerosol number concentration (Nait) and size. In contrast, seasonal variations in updraft velocity and aerosol hygroscopicity have weaker effects. These results help clarify how boundary-layer coupling and aerosol size distributions jointly regulate marine cloud droplet formation and provide observational constraints for representing aerosol-marine cloud interactions in climate models.