Statistical landslide susceptibility assessment in a dynamic environment: A case study for Lanzhou City,Gansu Province,NW China

This study presents a statistical landslide susceptibility assessment (LSA) in a dynamic environment. The study area is located in the eastern part of Lanzhou, NW China. The Lanzhou area has exhibited rapid urbanization rates over the past decade associated with greening, continuous land use change, and geomorphic reshaping activities. To consider the dynamics of the environment in the LSA, multitemporal data for landslide inventories and the corresponding causal factors were collected. The weights of evidence (WofE) method was used to perform the LSA. Three time stamps, i.e., 2000, 2012, and 2016, were selected to assess the state of landslide susceptibility over time. The results show a clear evolution of the landslide susceptibility patterns that was mainly governed by anthropogenic activities directed toward generating safer building grounds for civil infrastructure. The low and very low susceptibility areas increased by approximately 10% between 2000 and 2016. At the same time, areas of medium, high and very high susceptibility zones decreased proportionally. Based on the results, an approach to design the statistical LSA under dynamic conditions is proposed, the issues and limitations of this approach are also discussed. The study shows that under dynamic conditions, the requirements for data quantity and quality increase significantly. A dynamic environment requires greater effort to estimate the causal relations between the landslides and controlling factors as well as for model validation.     

Characteristics of earthquake-triggered landslides and post-earthquake debris flows in Beichuan County

Field investigations and aerial photography after the earthquake of May 12,2008 show a large number of geo-hazards in the zone of extreme earthquake effects.In particular,landslides and debris flows,the geo-hazards that most threaten post-disaster reconstruction,are widely distributed.We describe the characteristics of these geo-hazards in Beichuan County using high-resolution remote sensing of landslide distribution,and the relationships between the area and volume of landslides and the peak-discharges of debris flows both pre-and post-earthquake.The results show:1) The concentration(defined as the number of landslide sources per unit area:Lc) of earthquaketriggered landslides is inversely correlated with distance from the earthquake(DF) fault.The relationship is described by the following equation:Lc = 3.2264exp(-0.0831DF)(R2 = 0.9246);2) 87 % of the earthquake-triggered landslides were less than 15×104 m2 in area,and these accounted only for 50% of the total area;84% of the landslide volumes were less than 60×104 m3,and these accounted only for 50% of the total volume.The probability densities of the area and volume distributions are correlated:landslide abundance increases with landslide area and volume up to maximum values of 5 × 104 m2 and 30 × 104 m3,respectively,and then decreases exponentially.3) The area(AL) and volume(VL) of earthquake-triggered landslides are correlated as described with the following equation:VL=6.5138AL1.0227(R2 = 0.9131);4) Characteristics of the debris flows changed after the earthquake because of the large amount of landslide material deposited in the gullies.Consequently,debris flow peak-discharge increased following the earthquake as described with the following equation:Vpost = 0.8421Vpre1.0972(R2 = 0.9821)(Vpre is the peak discharge of pre-earthquake flows and the Vpost is the peak discharge of post-earthquake flows).We obtained the distribution of the landslides based on the above analyses,as well as the magnitude of both the landslides and the post-earthquake debris flows.The results can be useful for guiding post-disaster reconstruction and recovery efforts,and for the future mitigation of these geo-hazards.However,the equations presented are not recommended for use in site-specific designs.Rather,we recommend their use for mapping regional seismic landslide hazards or for the preliminary,rapid screening of sites.     

Regional landslide hazard assessment based on Distance Evaluation Model

There are many factors influencing landslide occurrence. The key for landslide control is to confirm the regional landslide hazard factors. The Cameron Highlands of Malaysia was selected as the study area. By bivariate statistical analysis method with GIS software the authors analyzed the relationships among landslides and environmental factors such as lithology, geomorphy, elevation, road and land use. Distance Evaluation Model was developed with Landslide Density （LD）. And the assessment of landslide hazard of Cameron Highlands was performed. The result shows that the model has higher prediction precision.     

Literature review and bibliometric analysis on data-driven assessment of landslide susceptibility

In recent decades, data-driven landslide susceptibility models(Dd LSM), which are based on statistical or machine learning approaches, have become popular to estimate the relative spatial probability of landslide occurrence. The available literature is composed of a wealth of published studies and that has identified a large variety of challenges and innovations in this field. This review presents a comprehensive up-to-date overview focusing on the topic of Dd LSM. This research begins with an i...     

Regional landslide hazard assessment based on Distance Evaluation Model

There are many factors influencing landslide occurrence. The key for landslide control is to confirm the regional landslide hazard factors. The Cameron Highlands of Malaysia was selected as the study area. By bivariate statistical analysis method with GIS software the authors analyzed the relationships among landslides and environmental factors such as lithology, geomorphy, elevation, road and land use. Distance Evaluation Model was developed with Landslide Density(LD). And the assessment of landslide hazard of Cameron Highlands was performed. The result shows that the model has higher prediction precision.     

Co-seismic landslide inventory and susceptibility mapping in the 2008 Wenchuan earthquake disaster area, China

The Ms 8.0 May 12,2008 Wenchuan earthquake triggered tens of thousands of landslides.The widespread landslides have caused serious casualties and property losses,and posed a great threat to post-earthquake reconstruction.A spatial database,inventoried 43,842 landslides with a total area of 632 km 2,was developed by interpretation of multi-resolution remote sensing images.The landslides can be classified into three categories:swallow,disrupted slides and falls;deep-seated slides and falls,and rock avalanches.The correlation between landslides distribution and the influencing parameters including distance from co-seismic fault,lithology,slope gradient,elevation,peak ground acceleration(PGA) and distance from drainage were analyzed.The distance from co-seismic fault was the most significant parameter followed by slope gradient and PGA was the least significant one.A logistic regression model combined with bivariate statistical analysis(BSA) was adopted for landslide susceptibility mapping.The study area was classified into five categories of landslide susceptibility:very low,low,medium,high and very high.92.0% of the study area belongs to low and very low categories with corresponding 9.0% of the total inventoried landslides.Medium susceptible zones make up 4.2% of the area with 17.7% of the total landslides.The rest of the area was classified into high and very high categories,which makes up 3.9% of the area with corresponding 73.3% of the total landslides.Although the susceptibility map can reveal the likelihood of future landslides and debris flows,and it is helpful for the rebuilding process and future zoning issues.     

Analysing post-earthquake landslide susceptibility using multi-temporal landslide inventories——a case study in Miansi Town of China

The earthquake that occurred on May 12, 2008, in Wenchuan County aroused a great deal of research on co-seismic landslide susceptibility assessment, but there is still a lack of an evaluation method that considers the activity state of the landslide itself. Therefore, this paper establishes a new susceptibility evaluation model that superimposes the active landslide state based on previous susceptibility evaluation models. Based on a multi-phase landslide database, the probabilistic approach was used to evaluate landslide susceptibility in the Miansi town over many years. We chose the elevation, slope, aspect, and distance from the channel as trigger factors and then used the probability comprehensive discrimination method to calculate the probability of landslide occurrence. Then, the susceptibility results of each period were calculated by superposition with the activity rate. The results show that between 2008 and 2014, the proportion of areas with low landslide susceptibility in the study area was the largest, and the proportionof areas with the highest susceptibility was minimal. The landslide area with highest susceptibility gradually decreased from 2014 to 2017. However, in 2017, 15.06% of the area was still with high susceptibility, and relevant disaster prevention and reduction measures should be taken in these areas. The larger area under the receiver operating characteristic curve(AUC) indicates that the results of the landslide susceptibility assessment in this study are more objective and reliable than those of previous models. The difference in the AUC values over many years shows that the accuracy of the evaluation results of this model is not constant, and a greater number of landslides or higher landslide activity corresponds to a higher accuracy of the evaluation results.     

On the initiation,movement and deposition of a large landslide in Maoxian County,China

At 5 am 24 th June 2017, a catastrophic landslide hit Xinmo Village, Maoxian County, Sichuan Province, China. The slide mass rushed down from an altitude of 3400 m and traveled 2700 m in a high velocity. The 13 million m~3 deposition buried the whole village and caused about 100 deaths. The source area of the landslide is located in a high steep slope, average slope angle is 40o and maximal angle is 65o. The strata are interbedded Triassic Zagunao Formation metamorphic sandstone and slate with the dip slope angle of 45°. Based on high-resolution satellite remote sensing image, UAV image, DEM data, and field investigation, failure mechanism, travel features, and deposit characteristics were analyzed. The results showed that this landslide was influenced by Songpinggou Fault zone. According to the topography before the failure, the landslide is located in the back scarp of an antecedent landslide induced by Diexi Earthquake in 1933. The bedding slope provided potential rupture surface. Historical seismic activities and long-term gravitational deformation caused rock mass accumulated damages. Weathering and precipitation weakened the rock mass and finally induced shearing and tension failure. A huge block detached from the top rock slope, pushed the past landslide deposits in the middle part, rushed out of the slope bottom in a high velocity and buried the Xinmo Village. The rapid movement entrained and brought the soil into the Songping Gully which recoiled with and bounced back from the opposite mountain.     

Numerical modeling and dynamic analysis of the 2017 Xinmo landslide in Maoxian County,China

A catastrophic landslide occurred at Xinmo village in Maoxian County, Sichuan Province,China, on June 24, 2017. A 2.87×106 m3 rock mass collapsed and entrained the surface soil layer along the landslide path. Eighty-three people were killed or went missing and more than 103 houses were destroyed. In this paper, the geological conditions of the landslide are analyzed via field investigation and high-resolution imagery. The dynamic process and runout characteristics of the landslide are numerically analyzed using a depth-integrated continuum method and Mac Cormack-TVD finite difference algorithm.Computational results show that the evaluated area of the danger zone matchs well with the results of field investigation. It is worth noting that soil sprayed by the high-speed blast needs to be taken into account for such kind of large high-locality landslide. The maximum velocity is about 55 m/s, which is consistent with most cases. In addition, the potential danger zone of an unstable block is evaluated. The potential risk area evaluated by the efficient depthintegrated continuum method could play a significant role in disaster prevention and secondary hazard avoidance during rescue operations.     

基于贝叶斯优化机器学习超参数的滑坡易发性评价

利用机器学习模型进行滑坡易发性评价时,不同的超参数设置往往会导致评价结果的不同。采用贝叶斯算法对4种常见机器学习模型(逻辑回归LR、支持向量机SVM、人工神经网络ANN和随机森林RF)的超参数进行了优化,探索了该算法对滑坡易发性机器学习模型的优化效果。以湘中地区4县(安化县、新华县、桃江县和桃源县)滑坡易发性评价为例说明该算法的可行性与适用性。基于滑坡历史编录,确定研究区内1 017个滑坡点,并选定15个滑坡影响因子,以此构建滑坡易发性模型的训练集和测试集。利用贝叶斯优化算法对4种机器学习模型的主要超参数进行了优化,依据优化后的超参数建立了4种优化模型,并使用AUC值等指标来比较其预测能力。结果表明：经超参数优化后的4种机器学习模型预测性能均有所提高,且基于贝叶斯优化的随机森林模型表现最好。     

Probabilistic seismic landslide hazard assessment: a case study in Tianshui,Northwest China

Probabilistic analysis in the field of seismic landslide hazard assessment is often based on an estimate of uncertainties of geological, geotechnical,geomorphological and seismological parameters.However, real situations are very complex and thus uncertainties of some parameters such as water content conditions and critical displacement are difficult to describe with accurate mathematical models. In this study, we present a probabilistic methodology based on the probabilistic seismic hazard analysis method and the Newmark's displacement model. The Tianshui seismic zone(105°00′-106°00′ E, 34°20′-34°40′ N) in the northeastern Tibetan Plateau were used as an example. Arias intensity with three standard probabilities of exceedance(63%, 10%, and 2% in 50 years) in accordance with building design provisions were used to compute Newmark displacements by incorporating the effects of topographic amplification.Probable scenarios of water content condition were considered and three water content conditions(dry,wet and saturated) were adopted to simulate the effect of pore-water on slope. The influence of 5 cm and 10 cm critical displacements were investigated in order to analyze the sensitivity of critical displacement to the probabilities of earthquake-induced landslide occurrence. The results show that water content in particular, have a great influence on the distribution of high seismic landslide hazard areas. Generally, the dry coverage analysis represents a lower bound for susceptibility and hazard assessment, and the saturated coverage analysis represents an upper bound to some extent. Moreover, high seismic landslide hazard areas are also influenced by the critical displacements. The slope failure probabilities during future earthquakes with critical displacements of 5 cm can increase by a factor of 1.2 to 2.3 as compared to that of 10 cm. It suggests that more efforts are required in order to obtain reasonable threshold values for slope failure. Considering the probable scenarios of water content condition which is varied with seasons, seismic landslide hazard assessments are carried out for frequent, occasional and rare earthquake occurrences in the Tianshui region, which can provide a valuable reference for landslide hazard management and infrastructure design in mountainous seismic zones.     

Landslide integrated characteristics and susceptibility assessment in Rongxian county of Guangxi,China

Landslides distribute extensively in Rongxian county, the southeast of Guangxi province, China and pose great threats to this county. At present, hazard management strategy is facing an unprecedented challenge due to lack of a landslide susceptibility map. Therefore, the purpose of this paper was to construct a landslide susceptibility map by adopting three widely used models based on an integrated understanding of landslide’s characteristics.These models include a semi-quantitative method(SQM), information value model(IVM) and logistical regression model(LRM).The primary results show that(1) the county is classified into four susceptive regions, named as very low, low, moderate and high, which covered an area of 13.43%, 32.40%, 31.19% and 22.99% in SQM, 0.86%, 26.82%, 44.11%, and 28.21% in IVM, 9.88%, 17.73%, 46.36% and 26.03% in LRM;(2) landslides are likely to occur within the areas characterized by following obvious aspects: high intensity of human activities, slope angles of 25°～35°, the thickness of weathered soil is larger than 15 m; the lithology is granite, shale and mud rock;(3) the area under the curve of SQM, IVM and LRM is 0.7151, 0.7688 and 0.7362 respectively, and the corresponding success rate is 71.51%, 76.88% and 73.62%. It is concluded that these three models are acceptable because they have an effective capability of susceptibility assessment and can achieve an expected accuracy. In addition, the susceptibility outcome obtained from IVM provides a slightly higher quality than that from SQM, LRM.     

Effects of the probability of pulse-like ground motions on landslide susceptibility assessment in near-fault areas

Earthquake-induced strong near-fault ground motion is typically accompanied by largevelocity pulse-like component, which causes serious damage to slopes and buildings. Although not all near-fault ground motions contain a pulse-like component, it is important to consider this factor in regional earthquake-induced landslide susceptibility assessment. In the present study, we considered the probability of the observed pulse-like ground motion at each site(PP) in the region of an earthquake as one o...     

Optimizing the frequency ratio method for landslide susceptibility assessment: A case study of the Caiyuan Basin in the southeast mountainous area of China

Bivariate statistical analysis of data-driven approaches is widely used for landslide susceptibility assessment, and the frequency ratio(FR) method is one of the most popular. However, the results of such assessments are dominated by the number of classes and bounds of landslide-related causative factors, and the optimal assessment is unknown. This paper optimizes the frequency ratio method as an example of bivariate statistical analysis for landslide susceptibility mapping based on a case study of the Caiyuan Basin, a region with frequent landslides, which is located in the southeast coastal mountainous area of China. A landslide inventory map containing a total of 1425 landslides(polygons) was produced, in which 70% of the landslides were selected for training purposes, and the remaining were used for validationpurposes. All datasets were resampled to the same 5 m × 5 m/pixel resolution. The receiver operating characteristic(ROC) curves of the susceptibility maps were obtained based on different combinations of dominating parameters, and the maximum value of the areas under the ROC curves(AUCs) as well as the corresponding optimal parameter was identified with an automatic searching algorithm. The results showed that the landslide susceptibility maps obtained using optimal parameters displayed a significant increase in the prediction AUC compared with those values obtained using stochastic parameters. The results also showed that one parameter named bin width has a dominant influence on the optimum. In practice, this paper is expected to benefit the assessment of landslide susceptibility by providing an easy-to-use tool. The proposed automatic approach provides a way to optimize the frequency ratio method or other bivariate statistical methods, which can furtherfacilitate comparisons and choices between different methods for landslide susceptibility assessment.     

采用多模型融合方法评价滑坡灾害易发性:以湖北省五峰县为例

不同的易发性评价模型可以得到有差异的滑坡空间预测结果，选取最优模型甚至综合各模型的优势是提高易发性评价精度的有效方法。为检验模型融合思路的有效性，以鄂西地区五峰县渔洋关镇为研究区，提取坡度、地层、断层、河流、公路等7个滑坡成因条件，分别采用信息量模型、证据权模型和频率比模型进行滑坡易发性评价；并将3种模型分别进行归一化、主成分分析（PCA，Principal component analysis）和优势融合，得到了6幅易发性分区图。结果表明:优势耦合模型精度最高（90.3%），频率比模型次之（89.7%），归一化融合模型和PCA融合模型分别为89.3%和89.1%，以上4种结果的精度均高于证据权模型（87.7%）和信息量模型（87.6%）；6幅预测图对应的评价结论与历史滑坡空间分布的实际情况相符。空间一致性对比结论表明，主成分融合模型与优势耦合模型的同格率高达68%，其预测结果避免了单个模型预测结论带来的偶然性和片面性，说明多模型融合方法与优势耦合模型在提高滑坡易发性预测精度上是可行性的，该思路对其他地区滑坡灾害易发性评价具有借鉴意义。      

Mapping landslide susceptibility at the Three Gorges Reservoir,China, using gradient boosting decision tree,random forest and information value models

This work was to generate landslide susceptibility maps for the Three Gorges Reservoir(TGR) area, China by using different machine learning models. Three advanced machine learning methods, namely, gradient boosting decision tree(GBDT), random forest(RF) and information value(InV) models, were used, and the performances were assessed and compared. In total, 202 landslides were mapped by using a series of field surveys, aerial photographs, and reviews of historical and bibliographical data. Nine causative factors were then considered in landslide susceptibility map generation by using the GBDT, RF and InV models. All of the maps of the causative factors were resampled to a resolution of 28.5 m. Of the 486289 pixels in the area,28526 pixels were landslide pixels, and 457763 pixels were non-landslide pixels. Finally, landslide susceptibility maps were generated by using the three machine learning models, and their performances were assessed through receiver operating characteristic(ROC) curves, the sensitivity, specificity,overall accuracy(OA), and kappa coefficient(KAPPA). The results showed that the GBDT, RF and In V models in overall produced reasonable accurate landslide susceptibility maps. Among these three methods, the GBDT method outperforms the other two machine learning methods, which can provide strong technical support for producing landslide susceptibility maps in TGR.     

Evaluation of deep learning algorithms for landslide susceptibility mapping in an alpine-gorge area: a case study in Jiuzhaigou County

With its high mountains, deep valleys, and complex geological formations, the Jiuzhaigou County has the typical characteristics of a disaster-prone mountainous region in southwestern China. On August 8, 2017, a strong Ms 7.0 earthquake occurred in this region, causing some of the mountains in the area to become loose and cracked. Therefore, a survey and evaluation of landslides in this area can help to reveal hazards and take effective measures for subsequent disaster management. However, differ...     

Assessment of landslide susceptibility using DBSCAN-AHD and LD-EV methods

Landslide susceptibility assessment plays a vital role in understanding landslide information in advance and taking preventive as well as control measures.The n...     

Optimization of causative factors using logistic regression and artificial neural network models for landslide susceptibility assessment in Ujung Loe Watershed,South Sulawesi Indonesia

Landslide susceptibility maps(LSMs) play a vital role in assisting land use planning and risk mitigation. This study aims to optimize causative factors using logistic regression(LR) and an artificial neural network(ANN) to produce a LSM. The LSM is produced with 11 causative factors and then optimized using forward-stepwise LR(FSLR), ANN, and their combination(FSLR-ANN) until eight causative factors were found for each method. The ANN method produced superior validation results compared with LR. The ROC values for the training data set ranges between 0.8 and 0.9. On the other hand, validation with the percentage of landslide fall into LSM class high and very high, ANN method was higher(92.59%) than LR(82.12%). FSLR-ANN with nine causative factors gave the best validation results with respect to area under curve(AUC) values, and validation with the percentage of landslide fall into LSM class high and very high. In conclusion, ANN was found to be better than LR when producing LSMs. The best Optimization was combination of FSLR-ANN with nine causative factors and AUC success rate 0.847, predictive rate 0.844 and validation with landslide fall into high and very high class with 91.30%. It is an encouraging preliminary model towards a systematic introduction of FSLR-ANN model for optimization causative factors in landslide susceptibility assessment in the mountainous area of Ujung Loe Watershed.