Air quality monitoring and assessment are essential issues for sustainable environmental protection. The monitoring process is composed of data collection, evaluation, and decision making. Several important pollution factors, such as SO2, CO, PM10, O3, NOx, H2S, location, and many others, have detrimental effects on air quality. Air quality cannot be precisely recorded and measured due to the total effect of pollutants that usually cannot be collectively prescribed by a numerical value. Therefore, evolution is required to take into account the complex, poorly defined air quality problems in which several naive and noble modeling approaches are used to evaluate and solve. In this study, hybrid data-driven machine learning, and neuro-fuzzy methods are integrated for estimating the air quality in the urban area for public health concerns. 1771 data are collected during three years for each pollution factor, starting from June 1, 2016, till September 30, 2019. The Back-Propagation Multi-Layer Perceptron (BPMLP) algorithm was employed with the steepest descent approach to reduce the mean square error for training the algorithm of the neuro-fuzzy model. Levenberg-Marquardt (LM) approach was also employed as an optimization method with Artificial neural networks (ANNs) for solving nonlinear least-squares problems in this study. These approaches were evaluated by fuzzy quality charts and compared statistically with the US-EPA air quality standards. Due to the effectiveness and robustness of soft computing intelligent models, the public's early warning will be possible for avoiding the harmful effects of pollution inside the urban areas, which may reduce respiratory and cardiovascular mortalities. Consequently, the stability of air quality models was correlated with the absolute air quality index. The findings showed remarkable performance of ANFIS and ANN-based Air Quality models for High dimensional data assessment.