Application of GIS-Based Back Propagation Artificial Neural Networks and Logistic Regression for shallow Landslide Susceptibility Mapping in South China-Take Meijiang River Basin as an Example

Qing-Hua Gong,Jun Wang,Jun-Xiang Zhang

doi:10.2174/1874149501812010021

Abstract

Introduction: In this study, artificial neural network (ANN) model and logistic regression were applied to analyze susceptibility and identify the main controlling factors of landslide in Meijiang River Basin of Southern China. Methods: Methods: Eleven variables such as altitude, slope angle, slope aspect, topographic relief, distance to fault, rock-type, soil-type, land-use type, NDVI, maximum rainfall intensity, distance to river were employed as landslide conditioning factors in landslide susceptibility mapping. Both landsliding and non-landsliding samples were needed as training data for ANN model. 384 landslides and 380 non-landsliding point with no recorded landslides according to field investigation and survey data were chosen as sample data of ANN model. And ROC curve was applied to calculate the prediction accuracy. Results: The validation results showed that prediction accuracy rate of 82.6% exists between the susceptibility map and the location of the initial 384 landsliding samples. However, logistic regression analysis showed that the average correct classification percentage was 75.4%. The prediction results of ANN model in high sensitive zone is more accurate than the logistic regression model. Conclusion: Therefore, the ANN model is valid when assessing the susceptibility. The main controlling factors were identified from the eleven factors by ANN model. The slope, rock and land use type appeared to be the main controlling factors in landslide formation process in Southern China.

Highlights

In this study, artificial neural network (ANN) model and logistic regression were applied to analyze susceptibility and identify the main controlling factors of landslide in Meijiang River Basin of Southern China
The prediction results of ANN model in high sensitive zone is more accurate than the logistic regression model
The results show that the ANN model is feasible to susceptibility map

Summary

Introduction

Artificial neural network (ANN) model and logistic regression were applied to analyze susceptibility and identify the main controlling factors of landslide in Meijiang River Basin of Southern China. Landslides result in enormous casualties and huge economic losses in mountainous regions. According to the China Ministry of Land and Natural Resources, the landslide hazards resulted in almost 1000 deaths, hundreds of millions of dollars in direct economic loss, and inestimable indirect loss every year [1].There were 19,522 geological hazards from January to June in 2010 which leads to 464 people dead or missing and direct economic losses of around 18.6 billion Yuan (about 2.3 billion US dollars). Landslide susceptibility maps provides urban planners overview information of landslide prone areas [4]. Regional and medium-scale landslide susceptibility mapping have become an important topic for specialists of different disciplines, such as engineering geologists, planners, local administrations or decision makers, etc [5, 6]

Methods

Discussion

Conclusion