Urban development zones and their climate exhibit cyclical changes throughout the year. Climate change is linked to deforestation, vehicular emissions, industrial activity, and dust storms. The consequences of urban land use and transport system development, influencing local environmental quality in general, and air quality in particular, are well-known and alarming. So, an increase in pollutants in the environment affects human and animal health, along with leading to a continuous increase in temperature. Particulate matter with a diameter of less than 2.5 µm (PM2.5) is a ubiquitous air pollutant released by biomass burning, vehicle and cooking exhausts, industrial processes, and non-exhaust sources. Due to its small size, PM2.5 can penetrate both the upper and lower respiratory systems. The application of advanced decision-making tools is necessary to predict upcoming climate action and the increase in environmental degradation. This research examines the application of machine learning techniques in assessing the impact of environmental change. Deploying different algorithms helped in the prediction of concentrations of high-risk pollutants. Models were analysed and compared based on different parameters to observe the performance of the models. To address the need for emissions reduction for sustainable urbanisation and to improve air quality, innovative decision-making tools that can be used in practice are necessary. The experiences and needs of stakeholders in charge of urban gross pollutant emissions reduction were analysed through a dedicated device. Environmental Impact Analysis will help achieve sustainability goals, such as Climate Action (SDG13) and Good Health and Well-being (SDG3). The use of machine learning techniques will enhance the efficiency of environmental performance and urban development.