Machine Learning-Driven Internet of Things Systems for Real-Time Landslide Forecasting: A Systematic Analysis

Sahithi Kurma1, Email

Bhanu Prakash Saripalli1, Email

Karthik Guntha2

Peplluis Esteva De La Rosa1

Nirmala Golla3

Kesava Datta Garlapati1 

1School of Technology, Woxen University, Hyderabad, 502345, India
2Stanley College of Engineering and Technology for Women (Autonomous), Hyderabad, 500001, India
3Suresh Gyan Vihar University, Jaipur, 302017, India

 

Abstract

Landslides pose significant threats in mountainous terrains and mining regions, leading to loss of life and substantial economic damage each year. Slope stability is also important because it should be continuously monitored to detect and prevent such disasters earlier. The presented review examines the most common landslide monitoring methods, especially the combination of the Internet of Things (IoT) and Machine Learning (ML). IoT facilitates the collection and transmission of real-time data of deployed sensors and ML improves the analysis by identifying the patterns, detecting anomalies, and increasing the accuracy of landslide prediction. Although they are promising, some of the challenges associated with the current real-time systems include high energy consumption. This paper brings to light the combination of IoT and ML to provide a structured, efficient and cost-effective method of landslide monitoring and early warning, particularly in areas that are remote and dangerous, such as hillsides and mines. The paper shows that IoT-based solutions, which are augmented with machine learning, are more reliable, responsive, and scalable than traditional solutions.

Machine Learning-Driven Internet of Things Systems for Real-Time Landslide Forecasting: A Systematic Analysis