Common air quality modelling methods and applications: A review paper

Standard air quality modeling techniques get a full assessment through the comparison between deterministic approaches and statistical and machine learning-based methods. This review assesses both advantages and disadvantages of modeling techniques for standard air quality analysis according to their specific environmental applications. The air quality modeling field utilizes box models for creating basic models of pollutant movement inside air volume boundaries. Emission, transport, transformation, and removal of pollutants are analyzed to determine pollutant concentrations. These processes take place in a box, in which uniform mixing of pollutants is presumed. Based on their simple design, box models make them useful tools for determining pollutant concentrations throughout urban areas. The evaluation process discusses box model effectiveness in particular conditions, along with computational strategies that can advance its predictive capabilities. The study combines existing research and practical applications with the goal of supporting researchers and environmental agencies alongside policymakers in picking suitable modeling systems for air quality assessment and management. A summary of modern advances together with existing obstacles in this study offers essential knowledge to researchers, policymakers, and environmental regulators to perform strategic air pollution evaluations. In contrast to the earlier reviews, which find the general scope of the path modeling types, the present research puts specific emphasis on the less-researched line joining the box models with more distinct machine learning methodologies to increase the level of urban air quality forecasting. It fills the research gap concerning the assessment of such mixed methods that may increase the accuracy of the models and their applicability in the real world.