Enhancing the reliability of landslide early warning systems by machine learning

  title={Enhancing the reliability of landslide early warning systems by machine learning},
  author={Hemalatha Thirugnanam and Maneesha Vinodini Ramesh and Venkat Rangan},
This paper submits a report on the effective adoption of machine learning algorithms for enhancing the reliability of rainfall-induced landslides. The challenges involved in the design of reliable landslide early warning systems (LEWS) and the data-driven context for overcoming these challenges have been presented. The operation of LEWS is explained using the chain of five major components (i) Data collection, (ii) Data transmission, (iii) Modelling, analysis and forecasting, (iv) Warning, and… 

Knowledge Discovery of Global Landslides Using Automated Machine Learning Algorithms

A scenario-based ML knowledge discovery system for town planners, disaster recovery strategists, and landslide researchers, which is the first of its kind to provide a comprehensive understanding of global landslide data.

Recent Advances in Internet of Things Solutions for Early Warning Systems: A Review

The aim of the paper is to describe the adopted IoT architectures, define the constraints and the requirements of an Early Warning system, and systematically determine which are the most used solutions in the four use cases examined.

The use of digital technologies for landslide disaster risk research and disaster risk management: progress and prospects

In the past few decades, digital technologies have played a more and more important role in landslide disaster risk management. To identify the progress and future directions with regard to the use

Rainfall-induced landslide early warning system based on corrected mesoscale numerical models: an application for the southern Andes

Abstract. Rainfall-induced landslides (RILs) are an issue in the southern Andes nowadays. RILs cause loss of life and damage to critical infrastructure. Rainfall-induced landslide early warning

Application of deep learning algorithms in geotechnical engineering: a short critical review

This study presented the state of practice of DL in geotechnical engineering, and depicted the statistical trend of the published papers, as well as describing four major algorithms, including feedforward neural, recurrent neural network, convolutional neural network and generative adversarial network.

Land surface temperature (LST) and soil moisture index (SMI) to identify slope stability

Scientists widely use satellite images for scientific purposes, including investigation on earth science and environmental issues. Developing of many environmental models is due to replicating the

Precipitation Nowcasting using Generative Adversarial Networks

Radar extrapolation-based methods and machine learning models typically produce blurry precipitation nowcasts, which are unrealistic. To overcome these limitations, previous research has developed a



Adaptive Learning Techniques for Landslide Forecasting and the Validation in a Real World Deployment

Application of this forecasting algorithm in real-world can provide 24 h extra time for early warning which is a boon for government and public to prepare for landslides after early warnings.

An integrated methodology to develop a standard for landslide early warningsystems

A new standard consisting of seven sub-systems for landslide early warning, including risk assessment and mapping, dissemination and communication, establishment of the disaster preparedness and response team, development of an evacuation map, standardized operating procedures, and the building of local commitment to the operation and maintenance of the entire program are proposed.

A Real-time monitoring and early warning system for landslides in Southwest China

A realtime monitoring network and a computer-aided automatic early warning system for landslides are presented with details of their design and an example of application in the Longjingwan landslide, Kaiyang County, Guizhou Province, and recommendations are presented for other similar projects.

Monitoring strategies for local landslide early warning systems

The description and the analysis of the monitoring strategies implemented within local landslide early warning systems (Lo-LEWS) operational all around the world are described and a description of the most used monitoring parameters and instruments for issuing warnings is presented.

Territorial early warning systems for rainfall-induced landslides

Early warning strategies to cope with landslide risk

The key elements of numerous early warning strategies implemented to cope with weather-induced landslide risk around the world are presented, a coherent framework to classify and analyse landslide early warning systems are defined, and the Author’s most recent research experiences on these systems are highlighted.

Development Of Early Warning System For Rainfall-induced Landslide in Indonesia

A real-time monitoring for early warning of landslide has been developed in Banjarnegara Regency of Central Java, Indonesia. The fieldserver gathers the data from multiple sensors i.e. long-span

An Adaptive and Sustained Landslide Monitoring and Early Warning System

Areas prone to mass movement are widespread in Indonesia. The potential for landslide disasters in several regions is controlled by the geotechnical and geological conditions and triggered by high

Towards real-time landslide risk management in an urban area.

With an average annual rainfall in the range 1200mm 1800mm, landslides in Wollongong are triggered by periods of prolonged heavy rainfall. During such events, real-time pore water pressure, slope

Updating EWS rainfall thresholds for the triggering of landslides

In this paper, the updating of rainfall thresholds for landslide early warning systems (EWSs) is presented. Rainfall thresholds are widely used in regional-scale landslide EWSs, but the efficiency of