Thesis Abstract

Abstract
Landslides are natural hazards that pose significant risks to communities residing in mountainous regions. Understanding and predicting landslide susceptibility is crucial for effective risk management and mitigation strategies. This thesis focuses on the analysis of landslide susceptibility in a mountainous region using machine learning techniques. The study area selected for this research is characterized by complex terrain and a history of landslide occurrences, making it an ideal case study for investigating landslide susceptibility. The primary objective of this research is to develop a predictive model that can effectively assess landslide susceptibility based on various contributing factors. Machine learning algorithms, such as Random Forest, Support Vector Machine, and Logistic Regression, will be utilized to analyze the relationships between landslide occurrences and potential influencing factors. These factors include topographic attributes, land cover types, soil properties, rainfall patterns, and historical landslide data. Chapter 1 provides an introduction to the research topic, background information on landslides, the problem statement, research objectives, limitations, scope, significance of the study, structure of the thesis, and definitions of key terms. Chapter 2 presents a comprehensive literature review covering ten key aspects related to landslide susceptibility, machine learning applications in geoscience, and previous studies on similar topics. Chapter 3 outlines the research methodology, including data collection methods, data preprocessing techniques, feature selection, model development, and model evaluation. This chapter also discusses the software tools and programming languages used in the analysis process. Chapter 4 presents the detailed analysis of the findings obtained from the machine learning models. The results are interpreted and discussed in relation to the contributing factors of landslide susceptibility. The chapter also includes visualizations, tables, and graphs to illustrate the relationships between the input variables and the predicted landslide susceptibility. Chapter 5 summarizes the key findings of the study, draws conclusions based on the results, and provides recommendations for future research and practical applications. The limitations of the study are acknowledged, and suggestions for further improvements are proposed. The research findings aim to contribute to the field of geoscience and assist in enhancing landslide risk management strategies in mountainous regions. In conclusion, this thesis highlights the importance of utilizing machine learning techniques for analyzing landslide susceptibility and emphasizes the potential benefits of predictive modeling in landslide risk assessment. By integrating geospatial data and advanced analytical methods, this research aims to enhance our understanding of landslide dynamics and support decision-making processes for sustainable land use planning and disaster resilience in mountainous regions.

Thesis Overview