Expedite Quantification of Landslides Using Wireless Sensors and Artificial Intelligence for Data Controlling...

Area of Science:

• Geosciences and Environmental Monitoring
• Computer Science and Artificial Intelligence

Background:

• Large-scale in-house monitoring systems are enhanced by wireless network sensor technologies.
• Wireless Sensor Networks (WSN) are crucial for monitoring environmental variables like temperature, sound, and pressure.
• Existing land surveillance methods struggle with real-time data analysis for catastrophic events.

Purpose of the Study:

• To illustrate the effectiveness of Wireless Sensor Networks (WSN) combined with artificial intelligence (AI) for real-time landslide monitoring.
• To develop an alerting system for informing populations about impending landslide risks.

Main Methods:

• Utilized Wireless Sensor Networks (WSN) to monitor key landslide causative factors including precipitation, Earth moisture, pore-water-pressure (PWP), and motion in real-time.
• Integrated artificial intelligence (AI) algorithms, specifically Logistic Regression, for data analysis and prediction.
• Developed a system for remote management and real-time data interpretation.

Main Results:

• Demonstrated the capability of WSN and AI to effectively monitor landslide-inducing factors in real-time.
• The proposed system successfully processes environmental data to identify potential landslide risks.
• Real-time monitoring facilitates timely detection and analysis of landslide-prone areas.

Conclusions:

• WSN and AI integration provides a robust solution for real-time landslide monitoring and forecasting.
• The developed alerting system can proactively inform communities about dangerous landslide situations.
• This approach enhances land life surveillance and mitigates risks associated with catastrophic events.