ALaDIn: Shining a Light on Air Quality through Data Integration and Machine Learning

To achieve the necessary level of accuracy when measuring air pollution for scientific purposes, expensive and complicated instrumentation is required. Consequently, only federal, local governments and some industries, collect data of sufficient quality for research, and only for a small number of Air Quality components. This limitation makes it difficult to implement added value services, such as exposure and health assessments. Furthermore, due to increasing urban and peri-urban population density and consequent rise in air pollution, Air Quality management problems are becoming more complex. As a result, there is a
vital need for enhanced Air Quality and exposure monitoring capabilities. This has been severely hampered by the high cost of traditional monitoring stations and the lack of high resolution data.