Landslide Monitoring and Detection

Abstract

The project titled "Landslide Monitoring and Detection" aims to detect and monitor potential landslides using a combination of sensors and machine learning algorithms. The sensors used in this project are MQ, rainfall, vibration, soil moisture, DHT, and water flow sensors. These sensors collect data that is sent to an Arduino Uno, which then sends it to a Node MCU. The Node MCU sends the data to a Java server using NetBeans IDE, which stores the data in a text file. The machine learning algorithms used in this project are KNN, random forest, XGBoost, and decision tree. These algorithms are applied to the data in the text file, with a given threshold value based on training data, to determine which algorithm provides the best accuracy. The algorithm with the highest accuracy is then used as the result for landslide detection and monitoring. The use of multiple sensors and machine learning algorithms improves the accuracy of landslide detection and monitoring. The sensors provide real-time data that is continuously monitored and analyzed by machine learning algorithms. The results of this project can aid in preventing and mitigating the effects of landslides, which can cause significant damage to infrastructure and loss of life. This project has the potential to be implemented in areas prone to landslides, providing early warning systems and improving disaster management strategies.