Search

Landslide susceptibility mapping (LSM) research is vital for averting and mitigating regional landslide disasters. Nevertheless, there has been a lack of systematic analysis regarding LSM's developmental drivers. Utilizing SciMAT, a scientometric tool, we analyzed 1661 papers on LSM from the Web of Science core collection database, spanning 1993 to 2022. We employed cluster and thematic evolution analysis in SciMAT to unveil trends. The results indicate a consistent upward trend over the past three decades. LSM modeling methods, geological data, and contributing factors are major focal points. Notably, the evolution of LSM models, with a rising adoption of machine learning and deep learning for risk assessment, emerges as a central knowledge pathway. This study offers valuable insights to scholars by identifying literature gaps and highlighting crucial research directions, facilitating informed decision-making in the realm of LSM. SciMAT tool initially employs cluster analysis and thematic evolution analysis to pinpoint the current popular themes and evolutionary trends of landslide susceptibility. The main trajectory of knowledge lies in the progression of landslide modeling methods. The latest trend in landslide susceptibility research is centered on the use of deep learning techniques, particularly convolutional neural networks, to achieve precise risk zonation. The study aims to highlight critical research directions, predict the future of LSM technology, and provide guidance for scholars. [ABSTRACT FROM AUTHOR]

Landslide susceptibility assessment (LSA) is a significant part of landslide research, which plays an important role in preventing landslide disasters. It has gained an increasing attention in both the academic and practice fields for the past two decades. However, there have been few bibliometric analyses on this topic, although bibliometric analysis can inspire future researchers by exploring the overall characteristics of the published literature. This article aims at collecting and analyzing the information of the abstracts, authors, institutions, countries, journals, funds, and keywords of the recent 4,732 papers published from 1999 to 2021 in Web of Science (www.webofscience.com). In particular, latent Dirichlet allocation (LDA), a machine learning and text analysis method, is utilized to analyze the abstract of each article to identify the hottest research topics related to LSA. The results revealed that: (1) The amount of annual publications related to LSA generally shows an increasing trend, which accounts for about 22% of the total landslide publications in 2021; (2) The author of Pradhan B, the institution of the Chinese Academy of Sciences, the country of China, the journal of Natural Hazards and the funding agency of the National Natural Science Foundation of China, are the productive performers in each aspect of LSA; and (3) Machine learning methods have gained a rapid increase in LSA in recent five years, which have become the most popular research topic. [ABSTRACT FROM AUTHOR]

The coastline between Tetouan and Bou Ahmed in the northernmost Rif of Morocco and its hinterland has become immensely hazardous due to frequent triggering of diversified landslides from last two decades. This paper describes the potential application of a set of multisource data and the GIS platform for zoning and identifying anomalous areas prone to landsliding and its associated landslide hazards. For this purpose, Information value (IV), Statistical index SI (Wi), Weighting factors (WF) and Evidential belief function (EBF) models have been used in this study. Eleven conditioning factors such as elevation, slope, aspect, curvature, shaded/relief, proximity to streams, proximity to faults, proximity to roads, land use, lithology, annual rainfall and an inventory of 905 unstable spots were used to develop the spatial database for landslides susceptibility mapping (LSM). The factors have been used after a test of multi-collinearity. The Receiver Operating Characteristic (ROC) curve and the Area Under the Curve (AUC) methods were used for validation of the LSM. The AUC results showed good prediction accuracy for all models with a prediction rate of 78% (IV), 77% (SI), 73% (WF) and 70% (EBF) respectively. However, the results indicated that comparatively, the IV model followed by WI model is more precise and accurate for landslides susceptibility mapping than other models. According to the presented models, about 64% of the study area is located in high to very high landslide susceptible zone. The findings presented in this study are imperatively valuable especially wherein large development projects and land use planning activities are going on. [ABSTRACT FROM AUTHOR]

In this paper, an original methodology for landslide susceptibility mapping (LSM) is presented. It consists of bagging ensembles of artificial neural networks (ANNs) and random forests (RFs), and hybrid bagging ensembles of these models. It is applied on the area of the Itajaí-Açu river valley. In December 2020, there was an extreme rainfall in the region, which triggered landslides. The RF ensemble presented slightly higher accuracy (0.941) than the ANN ensemble (0.940), but the ANN ensemble had a more balanced relation between sensitivity (0.966) and specificity (0.915) than the RF ensemble (specificity = 0.992, sensitivity = 0.891). The mixed ANN-RF ensemble presented the higher accuracy of all (0.950), and a good balance between sensitivity (0.948) and specificity (0.951), being considered the best model within those analyzed. The hybrid ensemble, together with classification threshold adjustment, removed discrepancies on the maps between both models by attenuating them. [ABSTRACT FROM AUTHOR]

Susceptibility based on different landslide types has rarely been assessed. Therefore, this paper aims to compare the prediction performance of hybrid approaches by combining the logistic model tree (LMT) with Decorate, random subspace, and rotation forest ensemble techniques (De-LMT, RS-LMT, and RoF-LMT) for susceptibility assessments of different landslide types. The Yuzi River catchment along the eastern margin of the Tibetan Plateau was selected as the study area. In this catchment, 478 rockfalls and 167 landslides were identified, and further partitioned into training (70%) and validation (30%) datasets, respectively. Subsequently, 13 conditioning factors were initially considered, and then 11 and 8, respectively, were selected as the final rockfall and landslide influencing parameters to conduct susceptibility models through multicollinearity analysis and information gain. Finally, the model performances were evaluated by area under the receiver operating characteristic curves (AUC). The obtained results demonstrated that elevation and rainfall were most influential factors for rockfall and landslide. For the rockfall prediction, the De-LMT model achieved the best prediction accuracy with the highest AUC (0.939), followed by the RS-LMT (0.938), RoF-LMT (0.928), and LMT (0.919) models. For the landslide prediction, the De-LMT model (AUC = 0.931) outperformed and outclassed the RoF-LMT (0.926), RS-LMT (0.922), and LMT (0.915) models. Therefore, it is reasoned out that all models exhibited satisfactory performance (AUC > 0.9), and the De-LMT model was superior in rockfall and landslide spatial prediction. [ABSTRACT FROM AUTHOR]

Landslide susceptibility assessment is used to predict the occurrence probability of landslides, and the results can provide a scientific basis for preventing and reducing landslides. Traditional assessment models usually assume that the contribution degree of landslide influence factors is fixed throughout an entire study area. Therefore, the results can only compare the relative weights of the different influencing factors, thereby ignoring changes in their contributions in the study area. This paper introduces a geographically weighted logistic regression (GWLR) model to assess the susceptibility of study area to landslides, fully considers the spatial heterogeneity of the influencing factors, and further explores the spatial relationships between the influencing factors and landslide occurrence. Based on landslide data from Zhenxiong County, Yunnan Province, China, collected in 2015, we selected 10 influencing factors covering the five aspects of topographies and geomorphologies, geological structures, meteorological conditions, ecological environments and human activities and implemented multicollinearity and significance tests to obtain the most suitable factors required by the model. Then, the GWLR model was used to analyze the degrees of landslide susceptibility across Zhenxiong County. The results show that the area under the receiver operating characteristic curve (ROC) of the GWLR model was 0.904, which suggests that the model had a high prediction accuracy. In addition, the regression coefficient maps of the influencing factors based on the GWLR model reflected changes in the relative contributions of each influencing factor in the study area, providing a reference for managers to formulate targeted decision-making measures. [ABSTRACT FROM AUTHOR]

The concept of leveraging the predictive capacity of predisposing factors for landslide susceptibility (LS) modeling has been continuously improved in recent work focusing on computational and machine learning algorithms. This paper explores the predictive capacity of different approaches to LS modelling using artificial intelligence. The key objective of this study is to estimate a LS map for the Taleghan-Alamut basin of Iran using Credal Decision Tree (CDT)-based (i.e. CDT-Bagging, CDT-Multiboost and CDT-SubSpace) hybrid machine learning approaches, which are state-of-the-art soft computing approaches that are hardly ever utilized in the assessment of LS. In this study, we used eighteen landslide predisposing factors (LPFs) that we considered to be the most important local morphological and geo-environmental factors influencing the occurrence of landslides. We calculated the significance of each of the LPFs in the landslide susceptibility assessment using the Random Forest Method. We also employed the Receiver Operating Characteristic curve, precision, performance, map robustness measurement and selection of the best-fitting models. The results shows that, compared to the other models, the CDT-Multiboost is the excellent model in this perspective with an average area under curve (AUC) of 0.993 based on a 4-fold cross-validation. We, therefore, consider the CDT-Multiboost models to be an effective method for improving spatial prediction of LS where landslide scarps or bodies are not clearly identified during the preparation of landslide inventory maps. Therefore, it will be helpful for preparing future landslide inventory maps and mitigate landslide damages. [ABSTRACT FROM AUTHOR]

The assessment of landslide hazards is crucial for disaster prevention and mitigation, but it has not considered the dynamic influencing factors that trigger landslides. The timeliness and practical value of the assessment results still need to be further improved. This study constructed a dynamic landslide hazard assessment system using information value model, dynamic precipitation data, and Backpropagation Neural Network (BPNN) model. Taking the Qingjiang Reservoir landslide in Changyang County, Hubei Province, China as an example, based on dynamic precipitation data and the BPNN model were used to develop a dynamic landslide hazard prediction model, and the temporal assessment and spatial distribution results of slope unit hazards in the study area from the 1980s to the 2010s, 2025, and 2030 were evaluated and predicted. It is predicted that the percentage of very high and high areas in 2025 and 2030 will be 50.5% and 57.5% respectively. [ABSTRACT FROM AUTHOR]

Traditional landslide susceptibility assessment methods often rely on single models, which can be biased and less accurate. In this article, we introduce a two-tiered strategy to enhance landslide susceptibility predictions. Initially, we employ an ensemble stacking technique that combines the strengths of three machine learning classifiers. This combination leverages the support vector classifier (SVC) as the key meta-classifier to optimize and refine predictions. Subsequently, we integrate the extreme gradient boosting (XGB), random forest (RF) and gradient boosting decision tree (GBDT) models with SVC to create hybrid approaches. In this study, we evaluate and compare the effectiveness of six machine learning algorithms for predicting landslide susceptibility in Anhua County, Hunan Province, China. The results demonstrated that the stacking ensemble model outperforms traditional models. The XBGþSVC model achieves the highest AUC value (0.9468), which is followed by the GBDTþSVC (0.9316), RFþSVC (0.9162), XGB (0.9393), GBDT (0.9009), and RF (0.8693). These findings indicate that stacking machine learning approaches hold promise for landslide susceptibility mapping. [ABSTRACT FROM AUTHOR]

The periodic storage and release of water in reservoirs have the potential to accelerate deformation or trigger ancient landslides. Interferometric synthetic aperture radar (InSAR) technology, renowned for its wide coverage and high precision, has emerged as an effective technique for the identification and monitoring of landslides. This study utilized spaceborne InSAR technology to identify and interpret landslides in the Liujiangxia reservoir area in China, leading to the detection of a total of 20 landslides. Moreover, among these 20 landslides, the landslide with substantial deformation (LJX02) was chosen, and the wavelet quantitative analysis technique was employed to investigate the correlation and time lag between various elevation positions of this landslide, the reservoir water level, and rainfall. The study successfully demonstrated that the deformation of the landslide lagged behind the reservoir water level by 152.10-182.50 days (from low to high elevation) and was delayed by 45.60-68.44 days compared to rainfall (from high to low elevation). [ABSTRACT FROM AUTHOR]

After the earthquake in Wenchuan in 2008, landslides have been happening frequently, causing a buildup of sediment in slopes and gullies. This creates a potential for mudslides and flash floods. It is important to create a model to assess the likelihood of landslides in Wenchuan County for disaster prevention. This study focuses on Wenchuan County, using 6180 co-seismic landslide sites as data. The relevant survey data is combined, and slope, normalized difference vegetation Index (NDVI), peak seismic acceleration (PGA), stream power index (SPI), topographic wetness index (TWI), distance from the road, distance from the fault, distance from the water system, relief intensity, aspect, curvature, land use type, and lithologic characters are chosen. The significance of the co-seismic landslide key influence factors is discussed. The study area's disaster susceptibility was assessed using the informative hierarchical analysis method model (I-AHP) and fully connected neural network (FCNN) model; the evaluation's findings mostly agreed with the survey's actual findings. The study's findings demonstrated that: (1) the FCNN model's AUC value was 0.910, while the I-AHP model's AUC value was 0.768, and the ROC curve and AUC value analysis indicated that the FCNN model outperformed the I-AHP model. (2) The three most significant influencing factors are lithology, topographic relief, and distance from roads; they account for 29.5%, 11%, and 10% of the total, respectively. Thus, landslide hazard research should be done in the high terrain undulating areas surrounding the road, and rock monitoring should be intensified in post-earthquake landslide-prone areas like Wenchuan County. (3) Given that Yingxiu Town is the epicentre of the region and that landslide disasters are highly likely to occur there, technical support for landslide disaster prediction, forecasting, safe prevention, and control in the area needs to be strengthened. [ABSTRACT FROM AUTHOR]

Landslide inventory incompleteness (LII) may significantly affect the model performance in landslide susceptibility mapping (LSM). However, traditional methods, including heuristic, statistical and deterministic models, cannot address LII issue. In this work, we introduce a novel hybrid LEO-MAHP model, blending landslide frequency, empirical adjustments, optimization functions, and multi-participated analytic hierarchy process to address it by taking Badong County as the study area. This hybrid model mitigates the drawbacks of data-heavy statistical approaches and subjective heuristic models by incorporating LII into weight determination. The findings show that the LEO-MAHP model demonstrates superior performance (AUROC = 0.809 and 0.805) over conventional statistical (AUROC = 0.714 and 0.770) and heuristic models (AUROC = 0.738 and 0.741) across different LII levels. We further discuss alternative LII solutions, proposing an updated landslide management strategy that accounts for climate change and human activities. Our findings underscore the necessity of evaluating LII before applying statistical or machine learning methods in LSM. List of Abbreviations: AHP: Analytic hierarchy process; AUROC: Area under receiver operating characteristic curve; CR: Consistency ratio; CI: Consistency index; CF: Conditional factor; DEM: Digital elevation model; FN: False negative; FP: False positive; FPR: False positive rate; InSAR: Interferometric Synthetic Aperture Radar; IV: Information value; LD: Landslide density; LII: Landslide inventory incompleteness; LS: Landside susceptibility; LSI: Landslide susceptibility index; LSM: Landslide susceptibility mapping; MAHP: Multi-participated analytic hierarchy process; MC: Model construction; MCDA: Multi-criteria decision analysis; MV: Model verification; MPP: Model prediction performance; ORS: Optical remote sensing; P&C: Prevention and control; PGA: peak ground acceleration; ROC: Receiver operating characteristic; RI: Random index; TN: True negative; TP: True positive; TPR: True positive rate. [ABSTRACT FROM AUTHOR]

The Karakoram Highway (KKH) is a pivotal gateway within the framework of the China-Pakistan Economic Corridor. Nevertheless, its distinct and intricate geographical characteristics make it susceptible to recurrent landslides. As an essential tool, landslide susceptibility mapping (LSM) is significant in managing and alleviating landslides near the KKH. Moreover, landslide conditioning factors (LCFs) are crucial determinants influencing the outcomes of LSM. However, existing methods primarily rely on machine learning algorithms, which do not adequately account for the intricate spatial characteristics and patterns between LCFs and landslide occurrences. In response, this study introduces the feature fusion transformer (FFTR) module, constructed based on the foundations of the transformer framework, to fuse the spatial information features of all LCFs. Subsequently, the abstract high-level spatial features obtained are fed into diverse machine learning classifiers, including random forest (RF), extreme gradient boosting (XGBoost), gradient boosting decision trees (GBDT), categorical boosting (CatBoost), and extremely randomized trees (ET), to generate landslide susceptibility maps. Displacement velocity calculated by Persistent Scatterer Interferometric Synthetic Aperture Radar (PSInSAR) is incorporated in the LSM. The results demonstrate that FFTR-RF achieves premium performance in the area under the curve (AUC) (94%), accuracy (87.31%), precision (87.21%), recall (88.02%), and F1-score (87.61%). Incorporating displacement velocity into LSM results predicted by models enhances the comprehensiveness of LSM. These methods will furnish early warning systems for landslide disasters along the KKH, thus aiding recommendations for mitigating landslides' social and economic losses. [ABSTRACT FROM AUTHOR]

This research aimed to assess landslide susceptibility in the Badakhshan province of Afghanistan, an area highly susceptible to landslides due to its complex topography and geological conditions. Three distinct machine learning (ML) models, namely the Generalized Linear Model (GLM), Maximum Entropy (ME), and Random Forest (RF), were employed to identify the key contributing factors to landslide occurrences in the study region. The dataset used in this study consisted of landslide conditioning factors and a landslide inventory map. The conditioning factors encompassed lithology, soil type, plane curvature, profile curvature, elevation, slope, aspect, precipitation, land use/land cover (LULC), distance to fault, river, road, Normalized Difference Vegetation Index (NDVI), Topographic Wetness Index (TWI), Terrain Ruggedness Index (TRI), and Standardized Precipitation Index (SPI). The landslide inventory map contained 177 landslide locations and 65 non-landslide points obtained from Google Earth. Each machine learning (ML) model was trained and implemented independently using 70% of the training data, with the results validated against the remaining 30% of the landslide inventory dataset. Ensemble results from GLM, ME, and RF were obtained using the median approach. All three models exhibited consistent performance and identified similar landslide-prone areas. Among the various factors studied, proximity to rivers emerged as the most influential factor contributing to landslides, followed by the distance to roads and slope gradient. The study revealed that the districts of Argo and Yaftali Sufla, near Faizabad, were identified as particularly susceptible to landslides, especially in the vicinity of large valleys. Out of the total study area of 3086.4 km2, ∼2162 km2 were deemed relatively safe from landslides, while 149 km2 (representing 4.8% of the study region) were identified as highly susceptible to landslides. Area Under the Receiver Operating Characteristic Curve (AUC) and Root Mean Square Error (RMSE) statistics were used to evaluate the performance of the machine learning (ML) algorithms. The RF and ME models demonstrated the highest performance levels. This research contributes to our understanding of landslide susceptibility in Badakhshan province and can aid in implementing effective landslide risk management strategies in the region. [ABSTRACT FROM AUTHOR]

Landslides in high-order position areas pose a serious threat to residents located below such areas. Therefore, research on the evolution process and underlying dynamic mechanisms is crucial. The majority of relevant studies are based on landslides that have already occurred; however, the investigation of potential landslides is of higher value. In this study, a progressive potential landslide identification method is proposed with the application of SBAS-InSAR (Small Baseline Subset Interferometric Synthetic Aperture Radar) and subsequently combined with Google Earth, GF-1 (Gaofen-1), GF-2 (Gaofen-2), ZY-3 (Ziyuan-3) and UAV (Unmanned Aerial Vehicle) imagery, and DEM (Digital Elevation Model) for further validation. The proposed method is employed to determine the potential landslide in Tuanjiecun by integrating the multi-period data to simultaneously analyze the evolution and mechanism of the potential landslide. The long short-term memory method is then adopted to predict the evolution trend based on accumulative deformation from SBAS-InSAR. The results suggest that the deformation of Tuanjiecun potential landslide will increase to −238.57 mm. This article provides a new approach for disaster prevention and mitigation by determining a potential landslide using composite remote sensing and predicting the development of the potential landslide on indirect contact monitoring. [ABSTRACT FROM AUTHOR]

The past landslides from landslide inventory are essential for machine learning (ML)-based landslide susceptibility assessment (LSA). They determine not only the positive samples (characterized by the past landslides) but also the negative samples (randomly generated based on past landslides) for training and validating the ML models. However, the number of past landslides is often limited because of the constraints of time, budget, and resources available, etc. In other words, the available data for establishing landslide susceptibility ML models are limited, which indicates that the accuracy and reliability of the corresponding models are insufficient. This article, therefore, proposes using a new landslide susceptibility index-based sampling strategy to enhance the positive and negative samples for model training and validation to reach an improved ML-based LSA. To realize this idea, landslide susceptibility analysis based on initial datasets compiled from landslide inventory by using three ML models, i.e., random forest (RF), gradient boosting decision tree (GBDT) and support vector machine (SVM), are first conducted to obtain the initial landslide susceptibility indices at different space locations. Then, the landslide susceptibility indices are analyzed with the proposed sampling strategy which considers directly the grid units with very high and very low landslide susceptibility indices as potential positive and negative samples, respectively, to enrich the initial dataset; and the number of these positive/negative samples is determined by a Bayesian optimization algorithm. Thereafter, the ML models are updated with the enriched datasets. Finally, to verify the effectiveness of the proposed strategy, the improved models are applied to assess the landslide susceptibility of Taojiang County, China, and the results are compared with those from initial corresponding models without updating. The results show that compared with the initial RF, GBDT and SVM models, the corresponding improved models have a better performance in accuracy, precision, recall rate, and specificity. In particular, the AUC values of the three models are increased by 11.94%, 10.72% and 0.57%, respectively. [ABSTRACT FROM AUTHOR]

The geomorphological control on landslides susceptibility maps (LSM) and frequency-area distributions (FAD) is under-investigated. Therefore, we investigate LSMs and FAD distributions in two contrasted landscapes of Taounate province using explanatory statistical techniques. In the geologically heterogenous context, our findings show that LSM spatial distributions for deep landslides are different to those of shallow processes, regardless of the LSM technique used. The Predictive factors also differ between both types of mass movements in this rugged and heterogenous zone. However, the opposite is observed in the geologically homogenous South, where shallow and deep landslides seem to be controlled by the same factors and tend to produce LSMs that are similarly distributed. This is further emphasized by the Area Under Curve (AUC) results which yield good to very good values in the South regardless of the types of landslides used for validation, with average to bad values in the North when shallow landslides are used to validate deep LSMs and vice versa. The same can be said about FADs, which are also sensitive to landscape variations. [ABSTRACT FROM AUTHOR]

Significant changes in the photosynthesis of terrestrial vegetation are observed in recent decades due to climate variability, land use and land cover changes, frequent disasters and anthropogenic forcing, but this situation in the Indian context remains largely unexplored. Here, therefore, we estimate the long–term changes in photosynthesis and its key climate drivers in India. The gross photosynthetic activity peaks (FPAR mean = 0.57) in post–monsoon (September, October and November) due to high soil moisture (87.26 kg/m² ), good precipitation (5.2 mm/day) and optimum temperature (21.46 C) conditions, whereas it is smallest (FPAR mean = 0.4) in summer (March, April and May) due to very high temperature (27.37 C) and lower soil moisture (55.45 kg/m2 ). The trend in FPAR over 2000–2019 reveals enhanced photosynthetic activity in India. In the northwest, both soil moisture and temperature have a positive influence on greening (i.e. moisture induced greening). Conversely, the unfavourable soil moisture and temperature conditions dominate in the peninsular region to trigger browning there (i.e. warming induced moisture stress). Our analyses suggest that the photosynthetic trend is primarily controlled by trend in the soil moisture (44.31%) and air temperature (32.54%). The warming induced moisture stress can be a serious threat in the future to drive browning in more areas. Extreme events such as droughts, landslides and fires are expected to increase in the hilly regions such as the northeast due to browning. Furthermore, as food production and forest resources influence the economy of a country like India, management and conservation of greenery are inevitable for a sustainable ecosystem. [ABSTRACT FROM AUTHOR]

Landslide predictive performance is expected to vary with different sampling techniques, such as landslide random and cluster sampling. Current advancements in remote sensing technologies and machine learning (ML) have enhanced landslide prediction performance. The Himalayan Mountain range in Pakistan poses an unadorned threat to the ecosystem and valley population because of landslide occurrence. The present study explores, and tests alternative sampling technique based on spatial pattern characterization in the wake of increased landslide prediction efficacy, rather than a renowned random technique for training and testing sampling. Thereupon, landslide inventory data with 17 geo-environmental factors (i.e. topographic, hydrological and seismic factors) were determined. Landslide cluster patterns were confirmed by the Nearest Neighbor Index (NNI) method and after getting the cluster patterns, the predicted performance of landslide sampling was tested using ML and statistical methods. Advanced ML algorithms including Random Forest (RF), Extreme Gradient Boosting (XGBoost), Naive Bayes (NB), K-nearest Neighbors (KNN) and statistical methods including Weight-ofEvidence (WofE) and Logistic Regression (LR) were used and validated. The landslide-prone district of Azad Jammu and Kashmir (Neelum Valley), Kashmir Himalayas, Pakistan, was selected as a case study. Prediction performance rates are high with area under the curve (AUC) ranging from 0.802 to 0.912; accuracy (ACC) ranges from 0.78 to 0.89, and kappa ranges from 0.50 to 0.68 with cluster sampling technique, whereas the performance was low with random sampling technique, with AUC ranges from 0.768 to 0.895; ACC ranges from 0.74 to 0.86 and kappa ranges from 0.48 to 0.64. The descending order of accuracy of the six algorithms was XGboost, RF, KNN, NB, LR and WofE. Our results confirmed that the landslides followed cluster patterns in the study area, and ML algorithms with cluster training samples positively affected landslide susceptibility prediction with a statistically significant difference. The outcomes support the hypothesis that using landslides spatial natural existence, as training samples instead of random concepts, improves the prediction ability; and highlights that alternative landslide partitioning technique could be a practicable and robust choice for landslides prediction modelling. [ABSTRACT FROM AUTHOR]

A major earthquake (6.9 Moment magnitude) occurred in the Sikkim and Darjeeling areas of the Indian Himalaya as well as in the adjacent Nepal on 18th September 2011, triggering a large number of landslides. A total of 188 landslide locations were extracted in order to create the landslide inventory map (LIM). The earthquake-induced landslide susceptibility maps (LSMs) were created using an Artificial Neural Network (ANN) model and three novel deep learning approaches (DLAs), namely Deep Boosting (DB), Deep Learning Neural Network (DLNN), and Deep Learning Tree (DLT), as well as training points and 22 conditioning factors. The earthquake-induced LSMs validated using several statistical indices and the results showed optimal accuracy for all models, where DB yielding the highest prediction rate curve (PRC) of 98.5%. This is followed by DLT (97%), DLNN (96%), and ANN (91%). The results demonstrate maximum efficacy of the proposed earthquake-induced LSM. [ABSTRACT FROM AUTHOR]

The machine-learning “black box” models, which lack interpretability, have limited application in landslide susceptibility mapping. To interpret the black-box models, some interpretable machine learning algorithms have been proposed recently. Among them is SHaply Additive ExPlanation (SHAP), which has attracted much attention because of its ease of operation and comprehensiveness. In this study, a novel interpretable model based on SHAP and XGBoost is proposed to interpret landslides susceptibility evaluation at global and local levels. The established evaluation model provided 0.75 accuracy and 0.83 AUC value for the test sets. The global interpretation shows that the peak rainfall intensity and elevation are the dominant factors that influence the occurrence of landslides in the study area. The combination of local interpretation and field investigations can provide a comprehensive framework for evaluating designated landslides, and it can also be used as a reference for preventing and managing the hazards of landslides. [ABSTRACT FROM AUTHOR]

Landslide susceptibility maps (LSMs) rely on statistical association for weighting the impact of each predictive factor class. However, the effects of using different training datasets and causative factors combinations on the accuracy of the results are rarely discussed. Accordingly, we investigated the effects of training data and computation technique selection on the accuracy and performance of LSMs. Results show that including relict landslides in the training data diminishes the accuracy of the LSMs compared to models that exclude such processes from the input. As for the effect of choosing different combinations of predictive variables, it was shown to be less significant. After investigating association and causality between predictive variables, the best performing models produced using frequency ratio and logistic regression tend to be more accurate than those including all variables. As for the artificial neural networks, it seems to outperform other models. Indeed, such investigations are beneficial for improving LSMs. [ABSTRACT FROM AUTHOR]

Machine learning methods are considered as most effective approaches to accomplish landslide susceptibility analysis around the globe. Landslide susceptibility maps (LSMs) have been frequently executed by statistical models in NW Himalaya. However, the comparison and applications of the statistical models with modern machine learning techniques has not been fully explored in this region. Hence, this study aims to compare the predicted performance of statistical and popular machine learning models to explore robust landslide prediction model in the landslide-prone area of NW Himalaya and investigate the compensations and limitations of these models to grasp a more precise and consistent result. This study presented machine learning approaches based on the artificial neural network (ANN), support vector machine (SVM) and logistic regression (LR) and the statistical methods based on the frequency ratio (FR), information value (InfoV) and weight of evidence (WoE). For this purpose, first an inventory map of 1507 landslides was prepared and randomly divided into training (70%) and testing (30%) dataset. Furthermore, 12 landslide conditioning factors (LCFs) were extracted from geospatial dataset to prepare thematic layers in ArcGIS. Thereafter, factor analysis was performed to eliminate colinear and least important variables which can mislead the results. The results showed that all selected LCFs are noncolinear and have significant contribution on landslides initiation, however, lithology, slope angle, annual rainfall and landuse were most influential factors. For modeling purpose, landslide inventory was correlated against all LCFs and trained into six models to produce respective LSMs. Finally, the performance of produced LSM models was validated and compared through area under receiver operating characteristic curve (AUROC), Accuracy, Recall, F1-score and Cohen's Kappa coefficients to assess the robustness of employed models. The results exhibit that the performance scores of machine learning models were considerably superior than statistical models. While, the AUROC values based on validation dataset indicate that LR (0.89) has better prediction ability followed by SVM (0.86), ANN (0.84), FR (0.83), InfoV (0.82) and WoE (0.81) in this study. Therefore, it is reasoned out that the machine learning methods are more reliable in generating adequate LSMs. However, the LR is recommended as most efficient model for predicting landslide susceptible zones in study region and thus can be considered as robust model for landslide susceptibility assessment in similar geo-environmental regimes. [ABSTRACT FROM AUTHOR]

Most previous studies of landslide susceptibility mapping (LSM) have not contemplated spatial heterogeneity and the commonly used models for LSM are aspatial, which could reduce model performance. Therefore, aiming to evaluate the applicability of spatial algorithms to predict landslide susceptibility, the performance of geographical random forest (GRF) was evaluated, in comparison to random forest (RF) and extreme gradient boosting (XGBoost). Based on the results, GRF presented the better performance (AUC = 0.876), followed by RF (AUC = 0.748) and XGBoost (AUC = 0.745). GRF also provided the most suitable susceptibility map. While RF and XGBoost presented almost 50% of the study area as susceptible, the GRF presented more concentrated susceptibility areas spatially, with a reasonable area for moderate (15.55%), high (8.73%) and very-high (2.59%) susceptibility classes. Finally, it can be inferred that spatial assessment may improve model performance, and that spatial models have a great potential for LSM. [ABSTRACT FROM AUTHOR]

Floods are the most dangerous natural disasters globally, occurring on a large scale, and cause significant economic and environmental damage. Therefore, determining flood susceptibility is essential to reducing the flood effects on human lives and materials. The main objective of this research is to develop a novel hybrid algorithm, through combining deep neural network and Manta ray foraging optimization (DNN-MRFO), to generate flood susceptibility map for Quang Ngai province, Vietnam. A geospatial distribution analytical approach was used to generate input data, including 2176 flood locations points and 13 influencing factors. A comparative analysis of the proposed model with five models namely DNN -- particle swarm optimization (DNN-PSO), DNN -- grey wolf optimization (DNN-GWO), DNN -- social spider optimization (DNN-SSO), support vector machine (SVM), gradient boosting regression (GBR) was carried out using different evaluation indices. The result shows that combining DNN and MRFO improved flood susceptibility classification precision with an area under the curve (AUC) of 0.98. The findings of this study are significant for supporting policymakers in understanding and identifying issues, which support improve their adaptation strategies. [ABSTRACT FROM AUTHOR]

The purpose of this study is to develop a reliable model for identification of flood susceptible areas. Three multi-criteria decision-making techniques, namely Analytical Hierarchy Process (AHP), Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), and Attributive Border Approximation Area Comparison (MABAC) methods combined with weight of evidence (WOE) were used in Babolroud Watershed, Iran. First, 50 flood locations were identified, of which 35 (70%) locations were selected randomly for modelling, and 15 (30%) locations were used for validation. Using GIS with eight conditioning factors including rainfall, distance from rivers, slope, soil, geology, elevation, drainage density and land use, the flood susceptibility maps were prepared. Area under receiver operating characteristic curve (AUROC) for test data of AHP-WOE, TOPSIS-WOE-AHP and MABAC-WOE-AHP methods were 72.8%, 90.5% and 81.6%, respectively, which indicate the reasonable accuracy of models. High accuracy of the proposed new model (MABAC) clarifies its applicability for preventive measures. [ABSTRACT FROM AUTHOR]

Northern Pakistan is a rugged mountainous area that is seismically active, high gradients, disintegrated lithology, and glaciers in the high peaks. District Ghizer lies among the most vulnerable areas and experience landslides every year due to different causative factors. This study has carried out to prepare a detailed landslide inventory and to develop a susceptibility model for the area. The most followed and probabilistic approach, Frequency Ratio (FR) model and a semi-qualitative Analytical Hierarchy Process (AHP) approach were applied to find the correlation between causative factors and mapped landslides. Persistent Scatterer Interferometry (PSI) Interferometric Synthetic Aperture Radar (InSAR) technique was applied to check deformation movement in the susceptible zones of extracted models, which showed the high Line of Sight (LOS) deformation velocity in high susceptible zones of both models. The extracted Landslide Susceptibility Index (LSI) models showed 82.82% and 73.43% of prediction accuracy for FR and AHP method calculated by Area Under Curve (AUC) of Receiver operating characteristic (ROC) method. The models revealed Slope, barrenness, and Geology are the main causative factors of landslide activities in the study area. Finally, both Landslide susceptibility index maps were classified into five susceptibility classes. As the study area is very prone to landslide disasters so these susceptibility models will be helpful to delineate hazardous zones for the medication of future landslides disasters in the area as well as it can be used as a tool in the planning strategies by decision-makers in development projects in the area. [ABSTRACT FROM AUTHOR]

This study evaluates and compares three machine learning models: K-Nearest Neighbour (KNN), Random Forest (RF) and Extreme Gradient Boosting (XGBoost) for landslide susceptibility mapping for part of areas in Rangamati District, Bangladesh. The performance of these methods has been assessed by employing statistical methods such as the area under the curve (AUC) for success rate (SR) and prediction rate (PR), Kappa index, Qs index and Friedman's test. Results show that XGBoost had the best performance with the highest AUC for both SR (95.27%) and PR (90.63%), followed by RF (SR: 89.26%; PR: 84.74%) and KNN models (SR: 85.54%; PR: 81.02%). This study provides a useful analysis for the selection of the best model for landslide susceptibility mapping and that it will be helpful for disaster planning and risk reduction. [ABSTRACT FROM AUTHOR]

The main aim of the present study was to produce and compare landslide susceptibility maps by using five machine learning techniques, namely, artificial neural network (ANN), logistic regression (LR), support vector machine (SVM), random forest (RF) and, classification and regression tree (CART). The study area was determined as the Arhavi-Kabisre river basin, a region in which the most landslide incidents occur in Turkey. Firstly, a landslide inventory was produced by identifying a total of 252 landslides. Secondly, a total of 11 landslide conditioning factors were considered for the landslide susceptibility mapping. Subsequently, the five machine learning techniques were constructed with the help of the training dataset for the landslide susceptibility maps. Finally, the receiver operating characteristic (ROC), sensitivity, specificity, F-measure, accuracy and kappa index were applied to compare and validate the performance of the five machine learning techniques. [ABSTRACT FROM AUTHOR]

Monitoring and determining landslides in dam reservoirs is very crucial as it is one of the main factors of dam failures in the world. Coruh river basin is one of the most important river basin in the Northeast part of Turkey which accompanies five big dams. Although persistent scatterer InSAR (PSInSAR) method is a powerful remote sensing technique which can measure and monitor displacements of the Earth's surface over time, its validation is a challenging issue because of the heterogeneous PS data. In this study, the efficiency of PSInSAR is investigated by proposing two different validation methods in order to see the consistency of the determined mean deformation velocities obtained with series of Sentinel-1A SAR-images. In the first method, 3D coordinates of reference points are projected to 1D displacement values in line of sight direction and then compared with the radar displacements of PS points. In the second method, new displacement values of PS points around reference points are identified from an interpolation map in order to be compared with the original displacements of reference points. In the end, it is showed that the displacements found by PSInSAR method are consistent with the reference points' displacements measured in the study area. Finally, this work's specific objectives are to present solutions to the challenging validation problem, to show the effectiveness of PSInSAR method and to describe the remaining challenges in PS analysis of landslide applications in dam areas. [ABSTRACT FROM AUTHOR]

The monitoring of pre-failure movements and their evolution over time is necessary to assess the predisposing and triggering factors. This research focusses on assessing terrain displacements in the Idukki district (Kerala, India) over a year before the deadly disaster, which occurred in August 2018; this disaster was claimed to be a dreadful one as it took off hundreds of human lives and properties. The post-event Persistent Scatterers interferometric analysis on a stack of 20 Sentinel-1 images was performed to analyse the precursory deformations of the landslides. From the results obtained, the study region is estimated to have undergone a displacement of -26 to +19 mm/year, which indicates the instability of the terrain. Also it is evident that the occurrence of the landslides in August 2018, has been due to the effect of the torrential rainfall and the increase in the pore water inducing instability, thereby causing displacement in the region. [ABSTRACT FROM AUTHOR]

The reduction of landslide losses requires appropriate method to reveal prone areas, causal factors and future occurrence likelihood. This study compared the effectiveness of the Statistical Index (SI), Certain Factor (CF) and Frequency Ratio (FR) models on landslide susceptibility mapping for Rwanda. Historical record and extensive field surveys generated an inventory map of 336 points. Thereafter, 245 and 91 points were randomly selected for building susceptibility and validation, respectively. Ten causal factors: elevation, slope angles, aspects, lithology, soil texture, distance to rivers, distance to roads, rainfall, land use/cover and normalized difference vegetation Index were analyzed. The area under curve (AUC) method revealed the training accuracies of 89.2%, 85.3% and 82.1% for the FR, CF and SI methods, respectively. And the prediction accuracies were 88.7%, 83.9% and 80.2% for the FR, CF and SI methods, respectively. Therefore, the FR performed well in landslide susceptibility mapping over the study area. [ABSTRACT FROM AUTHOR]