Abstract
Abstract. With the development of machine learning theory, more and more algorithms are evaluated for seismic landslides. After the Ludian earthquake, the research team combine with the special geological structure in Ludian area and the seismic filed exploration results, selecting SLOPE(PODU); River distance(HL); Fault distance(DC); Seismic Intensity(LD) and Digital Elevation Model(DEM), the normalized difference vegetation index(NDVI) which based on remote sensing images as evaluation factors. But the relationships among these factors are fuzzy, there also exists heavy noise and high-dimensional, we introduce the random forest algorithm to tolerate these difficulties and get the evaluation result of Ludian landslide areas, in order to verify the accuracy of the result, using the ROC graphs for the result evaluation standard, AUC covers an area of 0.918, meanwhile, the random forest’s generalization error rate decreases with the increase of the classification tree to the ideal 0.08 by using Out Of Bag(OOB) Estimation. Studying the final landslides inversion results, paper comes to a statistical conclusion that near 80% of the whole landslides and dilapidations are in areas with high susceptibility and moderate susceptibility, showing the forecast results are reasonable and adopted.
Highlights
Landslides are globally widespread phenomena, causing a significant number of human loss of life and injury, as well as extensive economic damages to private and public properties (Andrea Cimpalini, 2014)
Strong earthquake often triggered a large number of landslides, the secondary disasters caused a greater loss than earthquake itself (LI Zhong-sheng, 2003), early in the 1960s, some western developed countries have begun to study earthquake landslide as the main body of the geological disaster research (Carrara A, 1983)
With the development of technology, machine learning is gradually being introduced in the field of geological disaster prevention, multivariate statistical analysis (Saro Lee, 2002), artificial neural networks (Biswajeet Pradhan, 2007), fuzzy mathematics (Chung C F, 2008c) and other models have received a specific practice, these new theories provide us more ideas and methods, but the seismic landslide evaluation is still a worldwide problem, gives us heavy disasters
Summary
Landslides are globally widespread phenomena, causing a significant number of human loss of life and injury, as well as extensive economic damages to private and public properties (Andrea Cimpalini, 2014). Strong earthquake often triggered a large number of landslides, the secondary disasters caused a greater loss than earthquake itself (LI Zhong-sheng, 2003), early in the 1960s, some western developed countries have begun to study earthquake landslide as the main body of the geological disaster research (Carrara A, 1983). The landslide threatening earthquake rescue personnel and the local people’s life and property safety, without doubt, carrying out the analysis of earthquake landslide risk in Ludian is imminent and valuable for post-disaster relief and reconstruction
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
