The performance of using an autoencoder for prediction and susceptibility assessment of landslides: A case study on landslides triggered by the 2018 Hokkaido Eastern Iburi earthquake in Japan
Authors:
Open Access
- 11 December 2019
- journal article
- research article
- Published by Springer Nature in Geoenvironmental Disasters
- Vol. 6 (1) , 1-14
Abstract
Background: Thousands of landslides were triggered by the Hokkaido Eastern Iburi earthquake on 6 September 2018 in Iburi regions of Hokkaido, Northern Japan. Most of the landslides (5627 points) occurred intensively between the epicenter and the station that recorded the highest peak ground acceleration. Hundreds of aftershocks followed the major shocks. Moreover, in Iburi region, there is a high possibility of earthquakes occurring in the future. Effective prediction and susceptibility assessment methods are required for sustainable management and disaster mitigation in the study area. The aim of this study is to evaluate the performance of an autoencoder framework based on deep neural network for prediction and susceptibility assessment of regional landslides triggered by earthquakes. Results: By applying 12 sampling sizes and 12 landslide-influencing factors, 12 landslide susceptibility maps were produced using an autoencoder framework. The results of the model were evaluated using qualitative and quantitative assessment methods. The ratios of the sampling sizes on the non-landslide points randomly generated from the combination zone including plain and mountain (PM) and a mountainous only zone (M) affected different prediction abilities of the model’s performance. Conclusions: The 12 susceptibility maps, including the landslide susceptibility index, indicated the various spatial distributions of the landslide susceptibility values in both PM and the M. The highly accurate models explicitly distinguished the potential areas of landslide from stable areas without expanding the spatial extent of the potential landslide areas. The autoencoder is proved to be an effective and efficient method for extracting spatial patterns through unsupervised learning for the prediction and susceptibility assessment of landslide areas.Keywords
Funding Information
- Fawu Wang (JSPS-B-19H01980)
This publication has 60 references indexed in Scilit:
- Landslide Deformation Prediction Based on Recurrent Neural NetworkNeural Processing Letters, 2013
- Formation and deformation processes of late Paleogene sedimentary basins in southern central Hokkaido, Japan: Paleomagnetic and numerical modeling approachIsland Arc, 2009
- On the influence of temporal change on the validity of landslide susceptibility mapsNatural Hazards and Earth System Sciences, 2009
- Comparison of landslide susceptibility based on a decision-tree model and actual landslide occurrence: The Akaishi Mountains, JapanGeomorphology, 2009
- Landslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, ChinaGeomorphology, 2008
- GIS-based landslide susceptibility mapping using analytical hierarchy process and bivariate statistics in Ardesen (Turkey): Comparisons of results and confirmationsCATENA, 2008
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Application of logistic regression model and its validation for landslide susceptibility mapping using GIS and remote sensing dataInternational Journal of Remote Sensing, 2005
- The application of GIS-based logistic regression for landslide susceptibility mapping in the Kakuda-Yahiko Mountains, Central JapanGeomorphology, 2005
- The latest Cretaceous‐Early Paleogene rapid growth of accretionary complex and exhumation of high pressure series metamorphic rocks in northwestern Pacific marginJournal of Geophysical Research, 1994