Sensor data are increasingly used to monitor and observe spatiotemporal phenomena in a wide range of applications, such as flood management, urban traffic, air quality control, and forest fire management. Real-time modeling and representation of these evolving phenomena are fundamental for efficient and timely decision-making processes. In the context of multisensory systems, where two phenomena (e.g., air pollution index and wind conditions) can be sensed simultaneously by networked sensors, analyzing the relationships between them is a key issue for decision-making. Understanding whether the extent of pollution is expanding or contracting around a specific location, or whether it coincides with a windy zone, can support the adoption of more effective strategies. A sensing system equipped with a rule-based reasoning engine, capable of inferring spatiotemporal changes and the topological relationships between sensed phenomena with broad boundaries over time, provides decision-makers with precise and unambiguous information. In this paper, spatial changes and topological relationships for fuzzy-crisp objects representing phenomena with vague boundaries are conceptualized using an Extended Fuzzy Spatiotemporal Change Pattern (FESTCP) and a 5×5 Intersection Model (I5x5M), respectively. The rule-based reasoning engine proposed here is based on this conceptualization. To evaluate the method, a simulated case study of air pollution in Quebec City was conducted. The results demonstrate that the proposed approach effectively captures the spatiotemporal evolution of an air pollution episode, providing valuable information for real-time decision-making in real-world applications.