Forest fires and wildfires have become increasingly severe global challenges, exacerbated by factors such as climate change and extensive deforestation. These disasters not only devastate ecosystems and property but also pose significant threats to human lives. In emergency situation such as Forest-fire, the primary priority is the protection of people and the secondary priority is to protect the infrastructure. However, first responders often struggle to assess population density in affected areas due to limited access to up-to-date and reliable data. Accurate population density information is crucial for the efficient distribution of resources and strategic evacuation planning, which can significantly reduce casualties and enhance overall response effectiveness. This thesis introduces an innovative solution that leverages the capabilities of Mobile Network Operators (MNOs) to deliver exposure services directly to first responders, specifically tailored for forest fire scenarios. The proposed method eliminates the need for location-based exposure service of population density based on types of slice. It also eliminates the need for third-party applications by utilizing network slicing, a key feature of the 5G Core (5GC) network. By leveraging network slicing details, our approach effectively filters and organizes population density data based on types, ensuring the information provided is both relevant and accurate. Filtering data by device type is essential as it excludes IoT devices from population density calculations, assuming that each mobile device corresponds to a single person. In addition, filtering is further refined by incorporating factors such as type of devices in which the device is a vehicle or a person to get described type of population density according to the requirement. In addition we can also filter population density based on the location whether the device is indoor or outdoors, and different methods used to calculate its location. A crucial aspect of our methodology involves comparing the polygonal boundaries of device locations with defined areas of interest. This spatial analysis enables the precise determination of population density within targeted regions. By integrating this technique, first responders gain access to real-time and accurate population data, facilitating informed decision-making regarding emergency response strategies and resource allocation. Timely access to such data ensures that firefighting efforts are concentrated where they are most needed and that evacuation plans are implemented efficiently to maximize safety. Through this approach, we aim to significantly enhance the effectiveness of emergency operations during forest fire events. By providing first responders with direct access to reliable population density information sourced from MNOs, our solution improves disaster management capabilities and supports life-saving efforts. Ultimately, this method contributes to more efficient and effective responses to forest fires, thereby mitigating their impact on human lives and communities.
Vedant Santosh Rane (Wed,) studied this question.