Landslide Classification and Prediction of Debris Flow Using Machine Learning Models

Abstract

Landslides are unpredictable and destructive calamities that motivated the development of early warning systems to alert people and save their lives and property. A novel two-layer architecture is proposed to classify and predict landslides and types. The research is carried out in the Idukki district, Kerala, India, covering an area of 4358 km². Layer-1 uses topographical, hydrogeological, and meteorological features collected from various sources. The binary classifier in this layer classifies and predicts the probability of landslide occurrence. Layer-2 classifies landslides into debris flow, rockfall, and surficial slides and predicts debris flow through a multi-class classifier. To achieve better prediction accuracy, the landslide features that significantly influence the landslide occurrence of layer-1 are combined with layer-2. The Synthetic Minority Oversampling Technique is used to balance the database of minority categories. Classification and prediction are achieved using machine learning models such as the support vector machine, decision tree, random forest, and extreme gradient-boosting, and their performances are compared. The feature score for every feature of the model is calculated using the feature importance technique. The machine learning models are validated using the Area Under the Receiver Operating Characteristics curve and F1-score. On comparison, Extreme Gradient-Boost is found to perform well. Based on the prediction probability, the debris flow is classified into high-risk, medium-risk, and low-risk regions. This favored in identifying vulnerable areas and appropriate mitigation measures to reduce life loss and damage to infrastructure.

Keywords:

• Classification
• debris flow
• F1 score
• landslide susceptibility
• machine learning
• prediction

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

A. Shameem Ansar

A Shameem Ansar is currently working as an assistant professor in the Department of Computer Science Engineering at TKM College of Engineering, Kollam, Kerala, India. He completed her master of technology in wireless networks and applications at Amrita Vishwa Vidyapeetham, Amritapuri, India, and his bachelor of technology in computer science and engineering at the College of Engineering Trivandrum, Kerala, India. His primary research interests are machine learning, remote sensing, wireless network, and IoT.

S. Sudha

S Sudha is currently working as a professor in the Department of Electrical and Electronics Engineering at the National Institute of Technology Trichy, Tiruchirappalli, Tamil Nadu, India. She completed her PhD at NIT Trichy, Tiruchirappalli, India. She completed her ME in computer science and engineering and BE (electrical and electronics engineering) at NIT Trichy Tamil Nadu, India. Her research interests include wireless networks, operating systems, distributed computing, and artificial intelligence. Email: [email protected]

Savita Vinayagamoorthi

Savita Vinayaga Moorthi is currently working as a software developer at Citibank, Chennai. She completed her Bachelor of Technology in electrical and electronics engineering at the National Institute of Technology, Tiruchirappalli in 2021. Her primary interests are machine learning and data analytics. Email: [email protected]

Michelle Marianne Menachery

Michelle Marianne Menachery is currently working as a software developer at Deloitte USI, Bangalore, India. She completed her bachelor of technology in electrical and electronics engineering at the National Institute of Technology Tiruchirappalli, India. Michelle’s primary research interests lie in the fields of Machine Learning andArtificial Intelligence. She is particularly passionate about creating efficient data processing techniques and their application in diverse domains. Email: [email protected]

Suresh Francis

Suresh Francis is currently working as a scientist at Kerala State Remote Sensing and Environment Centre (KSREC), Trivandrum, Kerala, India, for the past 24 years. He completed PhD in remote sensing and landslides from Bharathidasan University, Tamilnadu, India, and completed a Master of Science (MSc) in geology/earth science. His research is in the field of resource evaluation, infrastructure development with ecosystem maintenance, vulnerability hotspot identification, disaster management, and GIS development (web and mobile) for the participatory digital transformation. Email: [email protected].