Planet Image-Based Inventorying and Machine Learning-Based Susceptibility Mapping for the Landslides Triggered by the 2018 Mw6.6 Tomakomai, Japan Earthquake

Abstract

The 5 September 2018 (UTC time) Mw6.6 earthquake of Tomakomai, Japan has triggered about 10,000 landslides with high density, causing widespread concern. We attempted to establish a detailed inventory of this slope failure and use proper methods to assess landslide susceptibility in the entire affected area. To this end we applied the logistic regression (LR) and the support vector machine (SVM) for this study. Based on high-resolution (3 m) optical satellite images (planet image) before and after the earthquake, we delineated 9295 individual landslides triggered by the earthquake, occupying an area of 30.96 km2. Ten controlling factors were selected for susceptibility analysis, including elevation, slope angle, aspect, curvature, distances to faults, distances to the epicenter, Peak ground acceleration (PGA), distance to rivers, distances to roads and lithology. Using the LR and SVM, two landslide susceptibility maps were produced for the study area. The results show that in the LR model, the success rate is 84.7% between the landslide susceptibility map and the training dataset, and the prediction rate is 83.9% shown by comparing the test dataset and the landslide susceptibility map. In the SVM model, a success rate of 90.9% exists between the susceptibility map and the test samples, and a prediction rate of 87.1% from comparison of the test dataset and the landslides susceptibility map. In comparison, the performance of the SVM is slightly better than the LR model.

Landslide Susceptibility Prediction Using Particle-Swarm-Optimized Multilayer Perceptron: Comparisons with Multilayer-Perceptron-Only, BP Neural Network, and Information Value Models

“…The ROC method has been commonly and successfully applied to landslide susceptibility prediction model evaluation [16,25,26]. An AUC ranging from 0.5 to 1 is the standard index of model prediction performance.…”

“…Along with the development of information technologies, remote sensing and the geographic information system (GIS) have gradually become data sources and spatial analysis platforms for LSP [6,7]. Based on remote sensing and GIS, many mathematical models have been proposed to calculate landslide susceptibility indices (LSI), such as the analytic hierarchy process [8][9][10], weight evidence method [11], information value (IV) theory [5,12], frequency ratio (FR) method [13,14], logistic regression model [7,15,16], logistic tree model [17], random tree [18,19], boosted tree [20], multi-criteria evaluation model [21], artificial neural networks (ANNs) [22][23][24], support vector machine (SVM) [25][26][27], and neuro-fuzzy method [28]. Although many models have been proposed for LSP, there is no model that is universally accepted and there is much room for improvement for these models.…”

Inventory, Distribution and Geometric Characteristics of Landslides in Baoshan City, Yunnan Province, China

“…The identification of recent landslides was mainly based on the differences in color and texture on remote sensing images. We used the following criteria in the landslide visual interpretation processes: (1) Due to surface disruption or loss of the vegetative cover, the reflectivity of recent landslides was higher than non-landslide areas, so the recent landslides could be easily distinguished by surface disruption or loss of vegetative cover [10,31]. (2) For the images of different years at the same location, we identified the images in different years one by one.…”

“…Detailed and accurate landslide inventory maps record the location, magnitude, characteristics, type of movement, estimated age and other information of slope failures, which are important for studies on spatial distribution of the landslides [3][4][5][6], impact on landform evolution [7][8][9], and landslide susceptibility mapping and hazard assessment [10][11][12][13]. Landslide inventory maps can be divided into event-based, multi-temporal and historical inventories [14,15].…”

Fault Slip Model of the 2018 Mw 6.6 Hokkaido Eastern Iburi, Japan, Earthquake Estimated from Satellite Radar and GPS Measurements

“…The largest aftershock's magnitude was M 5.9, which occurred only 3 h after the main shock. The earthquake also resulted in more than 10,000 landslides [3,4] and significant casualties, as well as heavy property losses. The mapped coverage areas of ascending (T068A and P112A) and descending (T046D and P018D) track interferometric synthetic aperture radar (InSAR) frames are shown in black dashed boxes.…”