Landslide Hazard Prediction Using Back Propagation Neural Networks With Optimization Of Genetic Algorithms

Landslides are one of the common geological disaster, which occur all over the world. It posed threats to people's life, property and the economic development. Some key issues should be thus resolved in both theory and prediction technique for landslide hazard assessment.In the last decades, the development of Geographic Information System (GIS) technology provides a method for the evaluation of landslide hazard. Through the use of direct-reverse DEM technology, the Changshougou valley was divided into 216 slope units, which includes 123 landslide units. According to mechanism analyses of landslides in the studied area, six environmental factors were selected to evaluate the landslide occurrence, such as elevation, slope, aspect, curvature, distance to rivers, and human activities. Each factor was extracted in terms of slope unit within the scope of ArcGIS. The spatial analysis shows that most of landslides in the Changshougou valley are located in the elevation of 100~150 meter, with an aspect of 135°~225°and 40°~60°in slope, and on convex slopes, which are also influenced by hydrological processing and human activities.After the spatial analysis of environmental factors, this thesis presents a case study for landslide hazard prediction, using back-propagation artificial neural network modeling optimized by genetic algorithms. From a database of 216 landslides, 120 landslides were used for training neural network models, and 96 landslides were used for the validation of landslide susceptibility. Comparing landslide presence with a susceptibility map, it was noted that the prediction accuracy of landslide occurrence is 93%, while units without landslide occurrence is predicted with accuracy of 81%. To sum up, the verification shows satisfactory agreement with accuracy of 86% between the susceptibility map and the landslide locations. In this case study, it was also found that some disadvantages can be overcome in the application of back-propagation neural networks, for example, the low convergence rate and local minimum, after the optimization was carried out using genetic algorithm. To conclude, Genetic algorithm-back propagation Neural Networks are an effective method to predict landslide hazard with high accuracy.