IoT and Cloud-Based Landslide Detection System Using Wireless Sensor Networks and Remote Sensing Data with Random Forest Algorithm

Abstract

One of the most damaging natural disasters, landslides seriously harm human life, the environment, and infrastructure. Early identification and To lower the dangers related to landslides, ongoing monitoring is crucial. In order to provide real-time environmental monitoring and prediction, this study suggests an Internet of Things (IoT) cloud-based landslide detection and monitoring system that combines Wireless Sensor Networks (WSN), remote sensing data, and machine learning approaches.. The system uses multiple environmental sensors, including a Soil Moisture sensor, Rainfall sensor, Ground Tilt sensor, Vibration sensor, Pore Pressure sensor, Temperature sensor, and Humidity sensor to monitor landslide-related parameters in real time.These sensor readings are transmitted through IoT devices to a cloud platform for storage and processing.To improve prediction accuracy, a Random Forest Machine Learning Algorithm is implemented to analyze the collected sensor data and identify patterns associated with potential landslide events. The model processes historical and real-time data to classify risk levels and generate early warning alerts. Experimental evaluation shows that the proposed system achieves an accuracy of approximately 95% in predicting landslide occurrences. The integration of IoT sensing technology, cloud computing, and Random Forest-based prediction enables efficient monitoring and timely alerts for disaster prevention. The proposed framework provides a low-cost, scalable, and reliable solution for landslide risk management in vulnerable regions.