The Internet-of-Things (IoT) is the key enabling technology for transforming current urban environments into so-called Smart Cities. One of the goals behind making cities smarter is to provide a healthy environment that improves the citizens{\textquoteright} quality of life and wellbeing. In this work, we introduce a novel data aggregation mechanism tailored to the application of large-scale air pollution monitoring with IoT devices. Our design exploits the intra- and inter-source correlations among air-pollution data using the framework of compressed sensing with side information. The proposed method delivers signi cant improvements in the data reconstruction quality with respect to the state of the art, even in the presence of noise when measuring and transmitting the data.