Assessment of earthquake-induced landslide inventories and susceptibility maps using slope unit-based logistic regression and geospatial statistics

AbstractInventories of seismically induced landslides provide essential information about the extent and severity of ground effects after an earthquake. Rigorous assessment of the completeness of a landslide inventory and the quality of a landslide susceptibility map derived from the inventory is of paramount importance for disaster management applications. Methods and materials applied while preparing inventories influence their quality, but the criteria for generating an inventory are not standardized. This study considered five landslide inventories prepared by different authors after the 2015 Gorkha earthquake, to assess their differences, understand the implications of their use in producing landslide susceptibility maps in conjunction with standard landslide predisposing factors and logistic regression. We adopted three assessment criteria: (1) an error index to identify the mutual mismatches between the inventories; (2) statistical analysis, to study the inconsistency in predisposing factors and performance of susceptibility maps; and (3) geospatial analysis, to assess differences between the inventories and the corresponding susceptibility maps. Results show that substantial discrepancies exist among the mapped landslides. Although there is no distinct variation in the significance of landslide causative factors and the performance of susceptibility maps, a hot spot analysis and cluster/outlier analysis of the maps revealed notable differences in spatial patterns. The percentages of landslide-prone hot spots and clustered areas are directly proportional to the size of the landslide inventory. The proposed geospatial approaches provide a new perspective to the investigators for the quantitative analysis of earthquake-triggered landslide inventories and susceptibility maps.

Download Full-text

GIS-Based Logistic Regression for Landslide Susceptibility Analysis in Western Washington State

International Journal of Applied Geospatial Research ◽

10.4018/ijagr.2017040101 ◽

2017 ◽

Vol 8 (2) ◽

pp. 1-19 ◽

Cited By ~ 1

Author(s):

Lucas A. Dailey ◽

Sven Fuhrmann

Keyword(s):

Logistic Regression ◽

Landslide Susceptibility ◽

Puget Sound ◽

Washington State ◽

Susceptibility Map ◽

The North ◽

Susceptibility Maps ◽

Western Washington ◽

Landslide Susceptibility Maps ◽

Puget Sound Region

The Oso landslide, one of the most recent disasters, occurred on March 22nd, 2014 in western Washington State. It caused significant property damage and killed over 40 people. As a result, a renewed interest has emerged for creating more accurate landslide susceptibility maps for this region. Research addressing landslide susceptibility within the north Puget Sound region of western Washington is lacking; therefore, this study develops a probabilistic GIS-based landslide susceptibility model for the north Puget Sound region. Multivariate logistic regression was utilized to create a landslide susceptibility map of Whatcom, Skagit, Snohomish, and King Counties. To predict probable areas of landslide occurrence, a landslide inventory map was prepared and fourteen topographic, geologic, environmental, and climatic predictor variables were considered. This research aims to assist in restructuring western Washington's landslide policies, and could serve as the first step in producing more accurate landslide susceptibility maps for the region.

Download Full-text

Landslide susceptibility mapping of Gdynia using geographic information system-based statistical models

Natural Hazards ◽

10.1007/s11069-021-04599-8 ◽

2021 ◽

Author(s):

Anna Małka

Keyword(s):

Logistic Regression ◽

Landslide Susceptibility ◽

Mass Movement ◽

Slope Angle ◽

Geographic Information ◽

Slope Aspect ◽

Susceptibility Map ◽

Conditioning Factors ◽

Susceptibility Maps ◽

Selection Of

AbstractThis work aims to prepare a reliable landslide susceptibility model and to analyse the factors contributing to landslides in a dynamic environment by considering the city of Gdynia, Poland as a case study. Geological, geomorphological, hydrological, hydrogeological, and anthropogenic predisposing factors are considered using geographic information systems. Ground types at different depths (1 m and 4 m b.g.l.) are used in the statistical susceptibility assessment for the first time. Landslide susceptibility maps are developed using two techniques in presenting landslides, 13 conditioning factors, and three statistical methods: landslide index, weight of evidence, and logistic regression. The considered factors have an influence on mass movement formation, but their roles are different. Many of these passive factors are interrelated and some of them are also related to active factors, i.e. triggers. Consideration of many thematic layers in the statistical approach allows for the selection of the most appropriate geo-environmental variables. The most significant conditioning factors that affect the likelihood of landsliding include land use and land cover as well as topography. The susceptibility maps generated by the index model and many interrelated passive factors appear to be over-predicted. The logistic regression model and only independent controlling factors (slope angle, slope aspect, and lithology) are sufficient to compile a reliable susceptibility map of Gdynia. Prediction rate curve plots show that the susceptibility map produced using logistic regression exhibits the highest prediction accuracy. The results emphasize the need to check independence in the selection of instability factors and the use of an independent subset of landslides for validation.

Download Full-text

Using landslide-inventory mapping for a combined bagged-trees and logistic-regression approach to determining landslide susceptibility in eastern Kentucky, United States

Quarterly Journal of Engineering Geology and Hydrogeology ◽

10.1144/qjegh2020-177 ◽

2021 ◽

pp. qjegh2020-177

Author(s):

Matthew M. Crawford ◽

Jason M. Dortch ◽

Hudson J. Koch ◽

Ashton A. Killen ◽

Junfeng Zhu ◽

...

Keyword(s):

Machine Learning ◽

Logistic Regression ◽

Standard Deviation ◽

Landslide Susceptibility ◽

Engineering Geology ◽

Susceptibility Mapping ◽

Landslide Inventory ◽

Landslide Susceptibility Mapping ◽

Susceptibility Map ◽

Landslide Occurrence

High-resolution LiDAR-derived datasets from a 1.5-m digital elevation model and a detailed landslide inventory (N ≥ 1,000) for Magoffin County, Kentucky, USA, were used to develop a combined machine-learning and statistical approach to improve geomorphic-based landslide-susceptibility mapping.An initial dataset of 36 variables was compiled to investigate the connection between slope morphology and landslide occurrence. Bagged trees, a machine-learning random-forest classifier, was used to evaluate the geomorphic variables, and 12 were identified as important: standard deviation of plan curvature, standard deviation of elevation, sum of plan curvature, minimum slope, mean plan curvature, range of elevation, sum of roughness, mean curvature, sum of curvature, mean roughness, minimum curvature, and standard deviation of curvature. These variables were further evaluated using logistic regression to determine the probability of landslide occurrence and then used to create a landslide-susceptibility map.The performance of the logistic-regression model was evaluated by the receiver operating characteristic curve, area under the curve, which was 0.83. Standard deviations from the probability mean were used to set landslide-susceptibility classifications: low (0–0.10), low–moderate (0.11–0.27), moderate (0.28–0.44), moderate–high (0.45–0.7), and high (0.7–1.0). Logistic-regression results were validated by using a separate landslide inventory for the neighboring Prestonsburg 7.5-minute quadrangle, and running the same regression function. Results indicate that 74.9 percent of the landslide deposits were identified as having moderate, moderate–high, or high landslide susceptibility. Combining inventory mapping with statistical modelling identified important geomorphic variables and produced a useful approach to landslide-susceptibility mapping.Thematic collection: This article is part of the Digitization and Digitalization in engineering geology and hydrogeology collection available at: https://www.lyellcollection.org/cc/digitization-and-digitalization-in-engineering-geology-and-hydrogeology

Download Full-text

InSAR Monitoring of Landslide Activity in Dominica

Remote Sensing ◽

10.3390/rs13040815 ◽

2021 ◽

Vol 13 (4) ◽

pp. 815

Author(s):

Mary-Anne Fobert ◽

Vern Singhroy ◽

John G. Spray

Keyword(s):

Risk Mitigation ◽

Disaster Mitigation ◽

Aerial Images ◽

Landslide Inventory ◽

Landslide Risk ◽

Susceptibility Map ◽

Interferometric Synthetic Aperture Radar ◽

Rainfall Events ◽

Susceptibility Maps ◽

Digital Elevation

Dominica is a geologically young, volcanic island in the eastern Caribbean. Due to its rugged terrain, substantial rainfall, and distinct soil characteristics, it is highly vulnerable to landslides. The dominant triggers of these landslides are hurricanes, tropical storms, and heavy prolonged rainfall events. These events frequently lead to loss of life and the need for a growing portion of the island’s annual budget to cover the considerable cost of reconstruction and recovery. For disaster risk mitigation and landslide risk assessment, landslide inventory and susceptibility maps are essential. Landslide inventory maps record existing landslides and include details on their type, location, spatial extent, and time of occurrence. These data are integrated (when possible) with the landslide trigger and pre-failure slope conditions to generate or validate a susceptibility map. The susceptibility map is used to identify the level of potential landslide risk (low, moderate, or high). In Dominica, these maps are produced using optical satellite and aerial images, digital elevation models, and historic landslide inventory data. This study illustrates the benefits of using satellite Interferometric Synthetic Aperture Radar (InSAR) to refine these maps. Our study shows that when using continuous high-resolution InSAR data, active slopes can be identified and monitored. This information can be used to highlight areas most at risk (for use in validating and updating the susceptibility map), and can constrain the time of occurrence of when the landslide was initiated (for use in landslide inventory mapping). Our study shows that InSAR can be used to assist in the investigation of pre-failure slope conditions. For instance, our initial findings suggest there is more land motion prior to failure on clay soils with gentler slopes than on those with steeper slopes. A greater understanding of pre-failure slope conditions will support the generation of a more dependable susceptibility map. Our study also discusses the integration of InSAR deformation-rate maps and time-series analysis with rainfall data in support of the development of rainfall thresholds for different terrains. The information provided by InSAR can enhance inventory and susceptibility mapping, which will better assist with the island’s current disaster mitigation and resiliency efforts.

Download Full-text

Hybrid Integration Approach of Entropy with Logistic Regression and Support Vector Machine for Landslide Susceptibility Modeling

Entropy ◽

10.3390/e20110884 ◽

2018 ◽

Vol 20 (11) ◽

pp. 884 ◽

Cited By ~ 28

Author(s):

Tingyu Zhang ◽

Ling Han ◽

Wei Chen ◽

Himan Shahabi

Keyword(s):

Support Vector Machine ◽

Logistic Regression ◽

Landslide Susceptibility ◽

Shaanxi Province ◽

Slope Aspect ◽

Support Vector ◽

Operating Characteristics ◽

Study Region ◽

Susceptibility Maps ◽

Landslide Susceptibility Maps

The main purpose of the present study is to apply three classification models, namely, the index of entropy (IOE) model, the logistic regression (LR) model, and the support vector machine (SVM) model by radial basis function (RBF), to produce landslide susceptibility maps for the Fugu County of Shaanxi Province, China. Firstly, landslide locations were extracted from field investigation and aerial photographs, and a total of 194 landslide polygons were transformed into points to produce a landslide inventory map. Secondly, the landslide points were randomly split into two groups (70/30) for training and validation purposes, respectively. Then, 10 landslide explanatory variables, such as slope aspect, slope angle, altitude, lithology, mean annual precipitation, distance to roads, distance to rivers, distance to faults, land use, and normalized difference vegetation index (NDVI), were selected and the potential multicollinearity problems between these factors were detected by the Pearson Correlation Coefficient (PCC), the variance inflation factor (VIF), and tolerance (TOL). Subsequently, the landslide susceptibility maps for the study region were obtained using the IOE model, the LR–IOE, and the SVM–IOE model. Finally, the performance of these three models was verified and compared using the receiver operating characteristics (ROC) curve. The success rate results showed that the LR–IOE model has the highest accuracy (90.11%), followed by the IOE model (87.43%) and the SVM–IOE model (86.53%). Similarly, the AUC values also showed that the prediction accuracy expresses a similar result, with the LR–IOE model having the highest accuracy (81.84%), followed by the IOE model (76.86%) and the SVM–IOE model (76.61%). Thus, the landslide susceptibility map (LSM) for the study region can provide an effective reference for the Fugu County government to properly address land planning and mitigate landslide risk.

Download Full-text

Landslides susceptibility modelling using Multivariate Logistic Regression Model in the Sahla Watershed in Northern Morocco

Sociedade & Natureza ◽

10.14393/sn-v33-2021-59124 ◽

2021 ◽

Vol 33 ◽

Author(s):

Mohammed El-Fengour ◽

Hanifa El Motaki ◽

Aissa El Bouzidi

Keyword(s):

Logistic Regression ◽

Landslide Susceptibility ◽

Slope Angle ◽

Google Earth ◽

Slope Aspect ◽

Multivariate Logistic Regression Model ◽

Susceptibility Map ◽

Potential Hazard ◽

Topographic Wetness Index ◽

Landslide Occurrence

This study aimed to assess landslide susceptibility in the Sahla watershed in northern Morocco. Landslides hazard is the most frequent phenomenon in this part of the state due to its mountainous precarious environment. The abundance of rainfall makes this area suffer mass movements led to a notable adverse impact on the nearby settlements and infrastructures. There were 93 identified landslide scars. Landslide inventories were collected from Google Earth image interpretations. They were prepared out of landslide events in the past, and future landslide occurrence was predicted by correlating landslide predisposing factors. In this paper, landslide inventories are divided into two groups, one for landslide training and the other for validation. The Landslide Susceptibility Map (LSM) is prepared by Logistic Regression (LR) Statistical Method. Lithology, stream density, land use, slope curvature, elevation, topographic wetness index, slope aspect, and slope angle were used as conditioning factors. The Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC) was employed to examine the performance of the model. In the analysis, the LR model results in 96% accuracy in the AUC. The LSM consists of the predicted landslide area. Hence it can be used to reduce the potential hazard linked with the landslides in the Sahla watershed area in Rif Mountains in northern Morocco.

Download Full-text

The Landslide Susceptibility Assessment using Bi-variate Statistical Information Value Model of Chenab River Valley, Jammu and Kashmir (India)

Disaster Advances ◽

10.25303/1411da4456 ◽

2021 ◽

Vol 14 (11) ◽

pp. 44-56

Author(s):

Abhijit S. Patil ◽

Bidyut K. Bhadra ◽

Sachin S. Panhalkar ◽

Sudhir K. Powar

Keyword(s):

Landslide Susceptibility ◽

Statistical Information ◽

River Valley ◽

Information Value ◽

Landslide Inventory ◽

Susceptibility Map ◽

Acceptable Result ◽

Information Value Model ◽

Value Model ◽

Chenab River

Almost every year, the Himalayan region suffers from a landslide disaster that is directly associated with the prosperity and development of the area. The study of landslide disasters helps planners, decision-makers and local communities for the development of anthropogenic structures in order to enhance the safety of society. Therefore, the prime aim of this research is to produce the landslide susceptibility map for the Chenab river valley using the bi-variate statistical information value model to detect and demarcate the areas of potential landslide incidence. The object-based image analysis method identified about 84 potential sites of landslides as landslide inventory. The statistical information value model is derived from the landslide inventory and multiple causative factors. The outcome showed that 23% area of the Chenab river valley falls into the class of a very high landslide susceptibility zone. The ROC curve method is used to validate the model which denoted the acceptable result for the landslide susceptibility zonation with 0.826 AUC value for the Chenab river valley.

Download Full-text

Landslide Susceptibility Mapping Using Statistical Methods along the Asian Highway, Bhutan

Geosciences ◽

10.3390/geosciences10110430 ◽

2020 ◽

Vol 10 (11) ◽

pp. 430 ◽

Cited By ~ 1

Author(s):

Sangey Pasang ◽

Petr Kubíček

Keyword(s):

Logistic Regression ◽

Landslide Susceptibility ◽

Area Under The Curve ◽

Information Value ◽

Weight Of Evidence ◽

Regression Methods ◽

Susceptibility Maps ◽

Road Corridors ◽

Landslide Susceptibility Maps ◽

Control Samples

In areas prone to frequent landslides, the use of landslide susceptibility maps can greatly aid in the decision-making process of the socio-economic development plans of the area. Landslide susceptibility maps are generally developed using statistical methods and geographic information systems. In the present study, landslide susceptibility along road corridors was considered, since the anthropogenic impacts along a road in a mountainous country remain uniform and are mainly due to road construction. Therefore, we generated landslide susceptibility maps along 80.9 km of the Asian Highway (AH48) in Bhutan using the information value, weight of evidence, and logistic regression methods. These methods have been used independently by some researchers to produce landslide susceptibility maps, but no comparative analysis of these methods with a focus on road corridors is available. The factors contributing to landslides considered in the study are land cover, lithology, elevation, proximity to roads, drainage, and fault lines, aspect, and slope angle. The validation of the method performance was carried out by using the area under the curve of the receiver operating characteristic on training and control samples. The area under the curve values of the control samples were 0.883, 0.882, and 0.88 for the information value, weight of evidence, and logistic regression models, respectively, which indicates that all models were capable of producing reliable landslide susceptibility maps. In addition, when overlaid on the generated landslide susceptibility maps, 89.3%, 85.6%, and 72.2% of the control landslide samples were found to be in higher-susceptibility areas for the information value, weight of evidence, and logistic regression methods, respectively. From these findings, we conclude that the information value method has a better predictive performance than the other methods used in the present study. The landslide susceptibility maps produced in the study could be useful to road engineers in planning landslide prevention and mitigation works along the highway.

Download Full-text

Landslide susceptibility mapping using Weight of Evidence Method in Haku, Rasuwa District, Nepal

Journal of Nepal Geological Society ◽

10.3126/jngs.v58i0.24601 ◽

2019 ◽

Vol 58 ◽

pp. 163-171 ◽

Cited By ~ 4

Author(s):

Arishma Gadtaula ◽

Subodh Dhakal

Keyword(s):

Landslide Susceptibility ◽

Google Earth ◽

Weight Of Evidence ◽

Slope Aspect ◽

Susceptibility Map ◽

Mountainous Area ◽

High Susceptibility ◽

Seismic Landslides ◽

2015 Gorkha Earthquake ◽

Very High

The 2015 Gorkha Earthquake resulted in many other secondary hazards affecting the livelihoods of local people residing in mountainous area. Plenty of earthquake induced landslides and mass movement activities were observed after earthquake. Haku region of Rasuwa was also one of the severely affected areas by co-seismic landslides triggered by the disastrous earthquake. Statistics shows that around 400 families were relocated from Haku Post-earthquake (MoFA, 2015). A total of 101 co-seismic landslides were focused during the study and were verified during the fieldwork in Haku village. The conditioning factors used in this study were slope, aspect, elevation, curvature (plan and profile), landuse, geology and PGA. The conditioning factor maps were prepared in GIS working environment and further analysis was conducted with the assistance of Google earth. This study used Weight of Evidence (WoE), a bivariate statistical model and its performance was assessed. The susceptibility map was further characterized into five different classes namely very low, low, high, medium and very high susceptibility zones. The statistical analysis obtained from the results of the susceptibility map prepared by using WoE model gave the results that maximum area percentage of landslide distribution was observed in medium and high susceptibility classes i.e. 38% and 33% followed by very high (13%), low (10%) and very low classes (5.8%) About 25% of the total landslides are separated to validate the prepared model used in the landslide susceptibility zonation. The overlay method predicts the reliability of the model.

Download Full-text

Wildfire susceptibility mapping via machine learning: the case study of Liguria Region, Italy

10.5194/egusphere-egu2020-18802 ◽

2020 ◽

Author(s):

Paolo Fiorucci ◽

Mirko D'Andrea ◽

Andrea Trucchia ◽

Marj Tonini

Keyword(s):

Machine Learning ◽

Natural Hazards ◽

Predisposing Factors ◽

Susceptibility Mapping ◽

Burned Area ◽

Susceptibility Map ◽

Susceptibility Maps ◽

Vegetation Heterogeneity ◽

Wildfire Susceptibility

Risk and susceptibility analyses for&#160; natural hazards are of great importance for the sake of&#160; civil protection, land use planning&#160; and risk reduction programs. Susceptibility maps are based on the assumption that future events are expected to occur under similar conditions as the observed ones. Each unit area is assessed in term of relative spatial likelihood, evaluating the potential to experience a particular hazard in the future based solely on the intrinsic local characteristics. These concept is well-consolidated in the research area related with the risk assessment, especially for landslides. Nevertheless, the need exist for developing new quantitative and robust methods allowing to elaborate susceptibility&#160; maps and to apply this tool to the study of other natural hazards.&#160; In&#160; the presented work, such&#160; task is pursued for the specific&#160; case of wildfires in Italy. The&#160; two main approaches for such studies are the adoption&#160; of physically based models and the data driven methods. In&#160; the presented work, the latter&#160; approach is&#160; pursued, using&#160; Machine Learning techniques in order to learn&#160; from and make prediction&#160; on the available information (i.e. the observed burned area and the predisposing factors) . Italy is severely affected by wildfires due to the high topographic and vegetation heterogeneity of its territory&#160; and&#160; to&#160; its&#160;&#160; meteorological conditions. The present study has as its main objective the&#160; elaboration of a wildfire susceptibility map for Liguria region (Italy) by making use of Random Forest, an ensemble ML algorithm based on decision trees. The quantitative evaluation of susceptibility is carried out considering two different aspects: the location of past&#160; wildfire occurrences, in terms of burned area, and the related anthropogenic and geo-environmental&#160; predisposing factors that may favor fire spread. Different implementation of the model&#160; were performed and compared. In&#160; particular,&#160; the effect of&#160; a pixel's&#160; neighboring land cover (including the type of vegetation and no-burnable area) on the output susceptibility map is investigated. In order to assess the&#160; performance&#160; of the model, the spatial-cross validation has been carried&#160; out, trying&#160; out different&#160; number of folders. Susceptibility maps for the two fire seasons (the&#160; summer&#160; and&#160; the winter&#160; one) were finally computed&#160; and validated. The&#160; resulting&#160; maps show&#160; higher susceptibility zones , developing closer to the coast in summer and along the interior part of&#160; the region in winter. Such zones matched well with the testing burned area, thus&#160; proving the&#160; overall&#160; good performance of the proposed method.REFERENCE Tonini M., D&#8217;Andrea M., Biondi G., Degli Esposti S.; Fiorucci P., A machine learning based approach for wildfire susceptibility mapping. The case study of Liguria region in Italy. Geosciences (2020, submitted)

Download Full-text