In today’s polluted environment, air pollution is one of the major challenges that must be controlled by adopting suitable precautionary measures and installing an appropriate number of air quality monitoring stations to safeguard human health. There are several causes of air pollution, including fossil fuels, automobiles, agricultural activities, domestic sources, mining, factories, and industries. These are typically measured in terms of common air pollutants such as \(\hbox {SO}_2\) , \(\hbox {NO}_2\) , \(\hbox {PM}_{2.5}\) , \(\hbox {PM}_{10}\) , \(\hbox {O}_{3}\) , CO. The main objective of this study is to assess air quality monitoring stations by evaluating some air pollution indices using multi-criteria group decision making (MCGDM). In formulating a decision-making problem, experts often face common challenges related to the availability of information, which may be insufficient, indeterminate, or vague, as well as their familiarity with the problem and the weights assigned to criteria, which may be partially or fully unknown. To address these issues, this study uses a picture fuzzy set (PFS) to quantify the insufficiency, indeterminacy, and vagueness of the available information. The confidence level is employed to reflect the expert’s familiarity with the problem, while the maximizing deviation method is applied to manage the uncertainty related to partially or fully unknown criteria weights. By integrating PFS with confidence levels, the paper introduces novel aggregation operators, including confidence picture fuzzy Einstein weighted, ordered weighted, and hybrid averaging operators. The essential properties of these operators, such as idempotency, monotonicity, and boundedness, are also verified. A MCGDM is then presented by combining the maximizing deviation method with the proposed novel aggregation operators in a PFS environment. Finally, a case study is conducted to evaluate three air quality monitoring stations. Sensitivity analysis is performed to assess the impact of varying combinations of experts’ confidence levels on the aggregated values. Additionally, a comparative analysis is carried out, contrasting the proposed aggregation operators with existing ones to demonstrate their effectiveness. The results conclude that the proposed operators are feasible, general, consistent, and can be effectively used to evaluate air quality monitoring stations.
