Hybrid deep learning model with enhanced sunflower optimization for flood and earthquake detection

Area of Science:

• Disaster Management
• Artificial Intelligence
• Geophysics

Background:

• Natural disasters like floods and earthquakes cause significant destruction and economic impact.
• Effective disaster preparedness requires robust monitoring and early warning systems.
• Current systems often lack the real-time capabilities needed for rapidly evolving natural events.

Purpose of the Study:

• To develop and evaluate a hybrid deep learning system for real-time monitoring of earthquake and flood-affected areas.
• To enhance the efficiency and accuracy of disaster detection using an improved optimization algorithm.
• To provide timely alerts to authorities and support emergency response efforts.

Main Methods:

• Utilized a hybrid deep learning approach for analyzing data from vulnerable regions.
• Implemented an improved sunflower optimization (ESFO) algorithm to optimize system performance.
• Conducted practical evaluations to determine optimal parameters for real-time earthquake detection.

Main Results:

• The proposed system effectively monitors earthquake- and flood-prone areas.
• The ESFO algorithm improved the efficiency of the deep learning model.
• Achieved real-time earthquake detection with a reduced false alarm rate.
• Demonstrated successful deployment in dynamic, real-world scenarios.

Conclusions:

• The developed hybrid deep learning system offers a viable solution for real-time natural disaster monitoring.
• The ESFO algorithm significantly enhances the performance of disaster detection models.
• The system provides a reliable tool for improving disaster preparedness and response.