Air pollution is one of the major concerns that plagues the world and has consequences in different spheres of our lives. Timely information regarding air pollution is sparse and often times goes unnoticed. The air quality data obtained from orbital sensor like Sentinel 5 and 5P TROPOMI and ground sensors (Central pollution control board sensors, CPCB) provide a large amount of information about the particle pollutants present in the atmosphere. This study used the previous 24 hours data to predict the next 24 hours of air pollutant concentration level for PM2.5, NO2, CO and SO2. The region of study is Delhi, North India because this region falls in the top ten most polluted cities worldwide. Convolutional neural networks (CNN) and long short-term memories (LSTM) are two examples of deep neural networks that have demonstrated significant advantages in tackling nonlinear spatiotemporal issues. They can accurately represent temporal and spatial information and extract useful contextual elements to integrate temporal properties. Therefore, we propose a combination of CNN and LSTM models for precise air quality prediction and validation in the region for the upcoming twenty-four hours based on data acquired on the preceding twenty-four hours.