The impact of air pollution on health and environmental sustainability is also negative and a reliable mechanism must be established to check the pollution levels and provide timely data to be used to make decisions. An Air Quality Monitoring and Alert System would help in such objectives by monitoring the key airborne pollutants which would include PM2.5 (fine particulate matter), PM10 (coarse particulate matter), carbon monoxide (CO), nitrogen dioxide (NO 2), sulfur dioxide (SO 2) and ozone (O 3) in ambient air based on sensors installed which will be equipped with Internet- of-Things (IoT) communication and are able to send wireless messages to alerts.. The pollution indicators derived via sensor measurement are processed via cloud-hosted information systems and/or edge computing nodes, as required for scalability, accuracy and low latency to deliver the sensor data. The Alert System architecture incorporates calibration algorithms, data preprocessing and machine learning models to dampen noise, isolate suspected conspicuous anomalies, and assist in forecasting increases in ambient air pollution in health risk indicators. Predictive modeling in combination with time-series analysis will enable detection of possible tendencies in pollution health risk indicators and help to initiate alerts before exceeding thresholds established.