Innovative Disaster Management: Predicting Flood-Prone Areas Using GIS and IoT Technologies

A study by the Faculty of Computers and Informatics, Zagazig University, Sharqiyah, Zagazig, Egypt focuses on improving disaster management strategies for flooding by using Geographic Information System (GIS) and Internet of Things (IoT) real-time data collected via drones. This research aims to identify the most flood-prone areas and determine optimal locations for drone takeoff and landing to enhance disaster preparedness and response. The study is conducted in two phases: prediction and site selection.

Phase 1: Flood Prediction: In the first phase, the study uses GIS and four forecasting models—Curve Fit Forecast, Exponential Smoothing, Forest-based Forecast, and a Convolutional Deep Neural Network (CDNN) model called InceptionTime—to predict which governorate along the Egyptian Mediterranean Coast is most susceptible to flooding. These models analyze historical data on rainfall and humidity to make predictions. The study finds that Port Said is the most vulnerable governorate to flooding.

Phase 2: Drone Site Selection: The second phase involves selecting the best locations for drone takeoff and landing using GIS and Multi-Criteria Decision Making (MCDM). The researchers employ the neutrosophic ordinal priority approach to weigh the optimal site selection criteria. This approach handles uncertainty in decision-making, providing a robust framework for identifying suitable locations for drones to operate during flood events.

Case Study: Egyptian Mediterranean Coast

The case study focuses on the Egyptian Mediterranean Coast, an area prone to flooding due to its geographical location. This region experiences severe flooding, especially during the winter months. The study aims to demonstrate the integration and effectiveness of GIS, IoT, and drone technologies in enhancing flood management strategies in this region.

By implementing the research framework, the study suggests the top 10 suitable sites for drone takeoff and landing in Port Said. The selection of these sites is based on the weighted criteria and sub-criteria evaluated through the MCDM model. The study acknowledges limitations such as data availability, reliability, and potential biases in the methodology, which are addressed to enhance the robustness of the framework.

IoT and GIS in Disaster Management

IoT plays a crucial role in disaster management by providing real-time monitoring, alerts, and data analysis. It helps in predicting disasters, enhancing response capabilities, and improving communication during emergencies. IoT technologies facilitate the collection and analysis of vast amounts of data, leading to more accurate predictions and timely responses. One of the key benefits of IoT-enabled disaster management is its ability to provide real-time alerts and historical data analysis, enabling authorities to identify areas requiring emergency services and critical relief.

GIS complements IoT by offering spatial analysis, mapping high-risk areas, and planning evacuation routes. It allows for the visualization and analysis of data on a map, assisting in identifying high-risk areas, planning evacuation routes, and allocating resources effectively. The integration of IoT and GIS provides a comprehensive approach to disaster risk management, enhancing the ability to respond to disasters more effectively.

Multi-Criteria Decision Making (MCDM)

The study uses MCDM to evaluate various criteria and sub-criteria for selecting optimal drone sites. The neutrosophic ordinal priority approach is particularly useful in handling uncertain and incomplete information, making it suitable for complex decision-making scenarios in disaster management. This method helps prioritize locations based on factors like accessibility, safety, and environmental conditions.

The MCDM model incorporates various criteria relevant to selecting the most suitable locations for drone takeoff and landing. The neutrosophic ordinal priority approach is used to weigh the criteria and sub-criteria, allowing for a more accurate and comprehensive evaluation of potential sites. This approach is crucial in disaster management, where decisions often need to be made quickly, under high stress, and with limited resources.

Practical Insights for Planning and Resource Allocation

The research provides a practical framework for enhancing disaster management strategies using GIS and IoT technologies. The study aims to improve disaster preparedness and response in the Egyptian Mediterranean Coast by predicting flood-prone areas and selecting optimal drone sites. The comprehensive approach outlined in this study can guide policymakers and disaster management authorities in developing better strategies to mitigate the impact of natural disasters.

The study's findings are particularly relevant for regions prone to flooding, where the integration of IoT, GIS, and advanced forecasting models can significantly enhance disaster risk management. The practical insights provided by this research can help improve planning, resource allocation, and decision-making processes, ultimately contributing to more resilient and prepared communities in the face of natural disasters.