Air quality and air pollution have a very large impact on human health. The sensitivity to different pollutants varies per person, therefore it is important that citizens can get personalised air quality information. The Personal Environmental Information System (PEIS) aims at delivering just that. The PEIS takes sensor data from several data providers and employs a service-oriented architecture to deliver these observations to the user through a smartphone application. The PEIS also uses scientific models to fuse the sensor data and create new, derived observations. To make scientific models that fuse sensor data fit better in a service-oriented architecture, a software framework called Fusion4Decision was developed. This framework is based on Open Geospatial Consortium standards and allows scientific models written in languages like MATLAB or R to be available as a web service.