Exploring machine learning and statistical approach techniques for landslide susceptibility mapping in Siwalik
Abhik Saha1, Lakshya Tripathi1, Vasanta Govind Kumar Villuri2
1Department of Mining Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad, 826004, India.
This study maps landslide susceptibility in Nainital, India, using GIS and statistical methods. The developed landslide susceptibility map (LSM) aids in disaster management and planning.
Area of Science:
- Geosciences
- Environmental Science
- Disaster Management
Background:
- Landslides pose significant risks to human life and infrastructure, particularly in mountainous regions like Nainital, Uttarakhand, India.
- Frequent landslides in Nainital cause substantial harm to livelihoods and settlements, necessitating proactive risk mitigation strategies.
Purpose of the Study:
- To develop a Landslide Susceptibility Map (LSM) for the Nainital area to aid in predicting and mitigating landslide occurrences.
- To assess and compare the effectiveness of various statistical methods integrated with GIS for landslide susceptibility mapping.
Main Methods:
- Geographic Information System (GIS) and statistical approaches, including Certainty Factor (CF), Information Value (IV), Frequency Ratio (FR), and Logistic Regression (LR), were employed.
- A comprehensive geodatabase was created using topographic data, satellite imagery, lithology, slope, aspect, curvature, soil, land use/land cover, geomorphology, drainage density, and lineament density.
- The accuracy of the predictive models was validated using the Receiver Operating Characteristic (ROC) curve analysis.
Main Results:
- All statistical models demonstrated satisfactory accuracy, with Area Under the Curve (AUC) values ranging from 84.8% to 87.8%.
- Logistic Regression (LR) achieved the highest accuracy (87.8%), followed closely by Certainty Factor (CF) at 87.6% and Information Value (IV) at 87.4%.
- Frequency Ratio (FR) also showed good predictive capability with an AUC of 84.8%.
Conclusions:
- The integration of GIS and statistical methods provides a robust framework for effective landslide susceptibility zonation.
- The developed landslide susceptibility maps are valuable tools for regional land-use planning and natural disaster management in landslide-prone areas.
- This study highlights the importance of multi-criteria analysis in understanding and mitigating landslide hazards.
More Related Videos
09:44Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon
Published on: October 16, 2018
08:27Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
Published on: January 5, 2024
Related Concept Videos
Manipulation and Analysis
Applications of GIS: Disaster Management and Emergency Response
Levels of Use of a GIS
Selected Data About Geographic Locations
Introduction to GIS
Methods of Obtaining Topography
