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

Abstract

Natural catastrophes may strike anywhere at any moment and cause widespread destruction. Most people do not have the necessary catastrophe preparedness knowledge or awareness. The combination of a flood and an earthquake can cause widespread destruction. Natural catastrophes have a domino effect on a country's economy, first by damaging infrastructure and then by taking human lives and other resources. The mortality tolls of both humans and animals have decreased as a result of recent natural disasters. So, we need a mechanism to identify and monitor floods and earthquakes. The suggested system uses a hybrid deep learning analysis to keep an eye on earthquake- and flood-affected areas. In order to boost the efficiency of the presented model, this research presents the improved sunflower optimisation (ESFO). In polynomial time, it determines the best time to schedule events. In view of the need for real-time monitoring of regions vulnerable to flooding and earthquakes, as well as the associated costs and precautions, this study focuses on systems. The suggested technology also sends a notification to the proper authorities whenever a person is detected in the area. In the event of an emergency, it can be used as a backup source of solar power. We then offer the best suitable depth and enable real-time earthquake detection with reduced false alarm rates through practical evaluation. Finally, we demonstrate that the projected model can be successfully deployed in a real-world, dynamic situation after being trained on a range of datasets.

Keywords

• Enhanced sunflower optimisation
• Hybrid deep learning
• Disasters identification
• Flood and earthquake
• Solar energy
• Warning and alert system