Landslide Susceptibility Models Research Articles

Pixel-Based Spatio-Statistical Analysis of Landslide Probability in Humid and Seismically Active Areas of Himalaya and Hindukush

The Hindukush and Himalaya regions of Pakistan are chronically prone to several geological hazards such as landslides. Studying landslides in these regions is crucial for risk assessment and disaster management, as well as for determining the effects of adverse climatic conditions, infrastructure management, and increasing anthropogenic activities. High-relief mountains in these regions face severe challenges because of frequently occurring landslides and other natural hazards, especially during intensive rainfall seasons and seismic activity, which destroy infrastructure and cause injuries and deaths. Landslides in the Alpuri Valley (Hindukush) and the Neelum Valley (Himalaya) have been activated through high magnitude earthquakes, intensive rainfalls, snowfall, floods, and man-made activities. Landslide susceptibility mapping in these areas is essential for sustainable development as it enables proactive risk management, up-to-date decision-making, and effective responses to landslide hazards, ultimately safeguarding human lives, property, and the environment. In this study, the relative effect method was applied for landslide susceptibility modeling in both study areas to determine the capability to reduce the effects of landslides, and to improve the prediction accuracy of the method. The relative effect is a statistical model that has only been used for very limited time for landslide susceptibility with effective results. A total of 368 (Neelum Valley) and 89 (Alpuri Valley) landslide locations were identified, which were utilized to prepare the reliable landslide inventory using GIS. In order to evaluate the areas at risk for future landslides activities and determine their spatial relationship with landslide occurrences, the landslide inventory was developed with 17 landslide causative factors. These factors include slope gradient, slope aspect, geology, plan curvature, general curvature, profile curvature, elevation, stream power index, drainage density, terrain roughness index, distance from the roads, distance from the streams, distance from fault lines, normalized difference wetness index, land-use/land-cover, rainfall, and normalized difference vegetation index. Finally, the performance of the relative effect method was validated using the success and prediction curve rate. The AUC-validated result of the success rate curve in the Alpuri Valley is 74.75%, and 82.15% in the Neelum Valley, whereas, the AUC-validated result of the prediction rate curve of the model is 87.87% in the Alpuri Valley and 82.73% in the Neelum Valley. These results indicate the reliability of the model to produce a landslide susceptibility map, and apply it to other landslide areas. The model demonstrated a more effective result in the Alpuri Valley, having a smaller area. However, the results are also desirable and favorable in Neelum Valley, with it being a large area. It will assist in general landslide hazard management and mitigation, and further research studies related to future landslide susceptibility assessments in other parts of the region.

Multi-model combination in key steps for landslide susceptibility modeling and uncertainty analysis: a case study in Baoji City, China

Reliable landslide susceptibility maps are essential for geohazard risk management. However, the selection of models and methods in the landslide susceptibility modeling (LSM) process is subjective and can lead to uncertainties in susceptibility outcomes. This paper introduces a framework for LSM and uncertainty analysis that leverages multiple models in key steps. The framework dynamically operates and combines models at each LSM step to generate susceptibility evaluation results from various method combinations. The uncertainty of different model combinations is then analyzed by comparing these results. The framework’s effectiveness is validated using Baoji City as a case study, examining the impact of different attribute interval numbers (AIN), non-landslide negative sample selection methods, and prediction models on susceptibility prediction outcomes. The results of each group show that the highest AUC value is 0.963 (AIN = 12, buffer-controlled sampling, Random forest) is about 0.26 higher than the lowest (no AIN, low-slope controlled sampling, Support vector machine). The findings suggest that the combinations involving larger AIN values, buffer-controlled sampling, XGBoost, or Random forest model yield relatively high AUC accuracy and relatively low uncertainty in the susceptibility index.

The influence of cartographic representation on landslide susceptibility models: empirical evidence from a Brazilian UNESCO world heritage site

The influence of cartographic representation on landslide susceptibility models: empirical evidence from a Brazilian UNESCO world heritage site

Synergetic use of geospatial and machine learning techniques in modelling landslide susceptibility in parts of Shimla to Kinnaur National Highway, Himachal Pradesh

Synergetic use of geospatial and machine learning techniques in modelling landslide susceptibility in parts of Shimla to Kinnaur National Highway, Himachal Pradesh

New method for landslide susceptibility evaluation in alpine valley regions that considers the suitability of InSAR monitoring and introduces deformation rate grading

ABSTRACT Incorporating Interferometric Synthetic Aperture Radar (InSAR) data sources into the landslide susceptibility evaluation process has yielded favorable outcomes in some studies. However, there are fewer analyses of the applicability of InSAR data monitoring, and a framework of accurate and effective grading criteria needs to be developed. To overcome these limitations, this study presents a novel and precise approach for landslide susceptibility assessment in alpine valley regions. This method incorporates the suitability of InSAR monitoring and introduces a grading system based on deformation rates, enhancing accuracy and efficiency. Taking the Dongchuan district, the most typical high mountain valley area in southwest China, as the research object, the SAR is quantitatively simulated and analyzed in this study using the improved R-index shadow layover method. Then, the optimal Synthetic Aperture Radar (SAR) monitoring scheme is derived, calculate deformation rates using LiCSBA (small baseline subset with the automated sentinel-1 InSAR processor) technology, and accurately establish the extent of landslide hazards (including potential landslides) by incorporating high-resolution images. The criteria for grading susceptibility within the landslide hazard range are based on deformation rates. Evaluation factors for corresponding grid cells are obtained. The best evaluation factors are selected using covariance diagnosis and gray correlation analysis. The landslide susceptibility model is developed utilizing the Particle Swarm Optimization-Back Propagation (PSO-BP) algorithm. It includes evaluation techniques for regions without deformation rates. The study findings demonstrate that: (i) Analyzing SAR suitability in alpine and canyon areas is crucial. Complementary monitoring with SAR lift tracks may only sometimes resolve geometric distortion issues in all these regions. (ii) The InSAR deformation rate can be an essential evaluation factor for landslide susceptibility evaluation. (iii) The proposed method effectively addresses low coherence challenges in certain alpine valley regions, where grading based on deformation rate is complex. The landslide susceptibility evaluation model is validated using performance evaluation indexes (Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and R-Square (R2)), confirming its reliability and effectiveness. (iv) The proposed method improves the grading accuracy by 37.84 ~ 60.91%. Overall, our proposed new landslide susceptibility method brings a new way of evaluating landslide susceptibility in alpine valley regions.

Delineating Non-Susceptible Landslide Areas in China Based on Topographic Index and Quantile Non-Linear Model

Efficient analysis of non-susceptibility to landslides targets regions with minimal or zero landslide probability, thereby obviating the need to estimate the likelihood for low-susceptibility zones. This study assesses the effectiveness of the quantile non-linear (QNL) model in delineating the non-susceptibility of landslides in China through a topographic index. The topographic index encompassed slope angle and topographic relief, which are calculated using a 3 × 3 and 15 × 15 square cell moving window, respectively. Additionally, a global landslide susceptibility model established using a comprehensive global landslide database and fuzzy algorithm was employed for comparative analysis, providing a holistic evaluation of the QNL model’s accuracy. The results show that while the overall distribution of the two QNL models for non-susceptible landslide areas was roughly consistent, notable discrepancies were observed in localized regions, especially in the Southwest and Qinghai-Tibet geological environment areas where landslides are prone to occur. The applicability of the QNL model is significantly limited in these areas. In addition, the predicted results of the QNL_CHN model are closer to those based on the global landslide susceptibility model of the fuzzy algorithm. This study provides valuable insights to enhance the QNL model’s applicability, thereby strengthening forest ecosystem management and mitigating ecological disaster risks.

Modelling antecedent soil hydrological conditions to improve the prediction of landslide susceptibility in typhoon-prone regions

AbstractMost regional landslide susceptibility models do not consider the evolving soil hydrological conditions leading up to a multiple occurrence regional landslide event. This results in inaccurate predictions due to the non-linear behaviour of the terrain. To address this, we have developed a simple and efficient model that incorporates the mid-term evolution of soil hydrological conditions. The model combines a water balance model and a geotechnical model based on infinite slope theory. The analysis of 561 high-intensity rainfall events in a typhoon-prone region of the Philippines revealed that the percolation of water during the 5-month wet season is crucial in determining landslide susceptibility. Consequently, high-intensity rainfall events at the start of the wet season are less likely to trigger landslides, while later events are more hazardous. We analysed the change in landslide susceptibility during the 2018 rainy season by comparing the probability of failure (PoF) before and after three high-intensity rainfall events (July, August and September). Only the event in September caused a significant increase in the probability of failure (PoF). The model showed an accuracy of 0.63, with stable cells better represented than unstable cells. The antecedent hydrological conditions on the lower soil layers are responsible for changes in landslide susceptibility. Our findings support the hypothesis that new approaches to developing hydro-meteorological thresholds for landslide early warning systems should be evaluated, especially in regions with strong seasonality.

Landslide susceptibility prediction and mapping in Loess Plateau based on different machine learning algorithms by hybrid factors screening: Case study of Xunyi County, Shaanxi Province, China

Machine learning models are widely used for landslide susceptibility prediction (LSP). To better develop a landslide susceptibility prediction model for the Loess Plateau, this study compared different machine-learning models (Logistic regression (LR), support vector machines (SVM), random forests (RF), Naïve Bayes (NB), and multilayer perceptron (MLP)). Using Xunyi County, China as the study area, 1096 landslides were collected and divided into a training set (70%) and a test set (30%). Significant influencing factors were selected from 20 landslide factors using GeoDetector. The relationships between these factors and landslides were determined by normalized frequency ratios. Five trained machine learning models calculated landslide susceptibility indices and generated landslide susceptibility maps. Additionally, the accuracy (ACC), precision (PRE), recall (REC), F1 score, AUC values, LSI distribution characteristics, and overlay analysis of historical landslides with LSM were used to evaluate the performance of the models. The results show that the LSP results of the five models are generally reasonable. The results further indicated that the use of GeoDetector was able to filter out the main factors of eolian landslides, improving the predictive performance of the model and obtaining better LSMs. The RF model had the best overall performance, followed by the SVM, and the MLP model created LSM high susceptibility zones that could contain the highest number of historical landslides. The q-values of factor contributions indicate that elevation, NDVI, rainfall, POI kernel density, and RDLS are the main factors controlling landslides, which need to be paid attention to for landslide control in the Loess Plateau region. The results of this study can provide a reference for the follow-up study of landslide prevention and control, especially landslide susceptibility modeling in the Loess Plateau.

Landslide susceptibility modelling in the Doda Kishtwar ramban (DKR) region of Jammu and Kashmir using remote sensing and geographic information system

The present study represents a significant understanding, employing cutting-edge Remote Sensing(RS) and Geographic Information System (GIS) technologies by conducting a comprehensive landslide susceptibility modelling in the Doda, Kishtwar, and Ramban (DKR) districts of the Union Territory of the Jammu and Kashmir in the NW Himalaya. The primary objective of this study is to determine the areas that are at high risk of landslides and accordingly classified these risk zones into five distinct categories, ranging from very high (VH) to very low (VL) susceptibility. To achieve this, a multifaceted approach, involving the utilization of various terrain thematic layers in the GIS environment was applied. The preferred framework employed in this study is the Weighted Overlay (WO) analysis. The final outcome of the study is the final landslide susceptibility map which is a significant and valuable resource for a wide range of stakeholders, including decision-makers, land managers, and local communities. It equips these stakeholders with the information and insights required to adopt proactive strategies in response to the identified landslide susceptibility zones.

Application of potential machine learning models in landslide susceptibility assessment: A case study of Van Yen district, Yen Bai province, Vietnam

Landslides are natural hazards that cause significant damage to both property and human lives. This study employs potential machine learning models such as Random Forest (RF), Gradient Boosting (GB), and Support Vector Machine (SVM) to assess landslide susceptibility in Van Yen District, Yen Bai Province, Vietnam, that experiences a higher frequency of landslides compared to other localities in the region. The study incorporates thirteen input variables, including elevation, slope angle, aspect, plan curvature, profile curvature, Topographic Wetness Index (TWI), distance to faults, lithology, distance to roads, distance to rivers, land cover, rainfall, and Normalized Difference Vegetation Index (NDVI). To construct the models, landslide statistics reports were utilized, consisting of 302 landslide points collected through field surveys and 52 landslide points determined using Radar Sentinel-1 images. The Google Earth Engine cloud computing platform is utilized for constructing the landslide susceptibility models. The outcome of the research is a landslide susceptibility map with five levels: very low, low, moderate, high, and very high. The Area Under the Curve (AUC) is used as a metric to evaluate the performance of all three models. The findings indicate that, besides similarities observed in landslide susceptibility maps for previously occurred landslides, the Random Forest model demonstrates a favorable performance compared to the other models, with an AUC of 0.883.

Probabilistic and physically-based modelling of rainfall-induced landslide susceptibility using integrated GIS-FORM algorithm

Probabilistic and physically-based modelling of rainfall-induced landslide susceptibility using integrated GIS-FORM algorithm

Space–time landslide hazard modeling via Ensemble Neural Networks

Abstract. Until now, a full numerical description of the spatio-temporal dynamics of a landslide could be achieved only via physically based models. The part of the geoscientific community in developing data-driven models has instead focused on predicting where landslides may occur via susceptibility models. Moreover, they have estimate when landslides may occur via models that belong to the early-warning system or to the rainfall-threshold classes. In this context, few published research works have explored a joint spatio-temporal model structure. Furthermore, the third element completing the hazard definition, i.e., the landslide size (i.e., areas or volumes), has hardly ever been modeled over space and time. However, technological advancements in data-driven models have reached a level of maturity that allows all three components to be modeled (Location, Frequency, and Size). This work takes this direction and proposes for the first time a solution to the assessment of landslide hazard in a given area by jointly modeling landslide occurrences and their associated areal density per mapping unit, in space and time. To achieve this, we used a spatio-temporal landslide database generated for the Nepalese region affected by the Gorkha earthquake. The model relies on a deep-learning architecture trained using an Ensemble Neural Network, where the landslide occurrences and densities are aggregated over a squared mapping unit of 1 km × 1 km and classified or regressed against a nested 30 m lattice. At the nested level, we have expressed predisposing and triggering factors. As for the temporal units, we have used an approximately 6 month resolution. The results are promising as our model performs satisfactorily both in the susceptibility (AUC = 0.93) and density prediction (Pearson r = 0.93) tasks over the entire spatio-temporal domain. This model takes a significant distance from the common landslide susceptibility modeling literature, proposing an integrated framework for hazard modeling in a data-driven context.

Feature adaptation for landslide susceptibility assessment in “no sample” areas

Given the time-consuming nature of compiling landslide inventories, it is increasingly important to develop transferable landslide susceptibility models that can be applied to regions without existing data. In this study, we propose a feature-based domain adaptation method to improve the transferability of landslide susceptibility models, especially in “no sample” areas. Two typical landslide-prone areas in Fujian province, southeastern China, were chosen as research cases to test the practicality of the transfer effect. Five conventional machine learning algorithms (Support vector machines (SVM), Random Forest (RF), Logistic Regression (LOG), K-nearest neighbor (KNN), and Decision tree (C4.5)) are used to model landslide susceptibility in sampled areas (source domain), and a feature transfer-based landslide susceptibility evaluation model is constructed under coupled feature transfer methods to evaluate the susceptibility of landslide in un-sampled areas (target domain). The results showed that feature transfer can effectively improve the transferability of different machine learning models for cross-regional prediction (The indicators have improved overall by 8.49%), with SVM (increased by 13.68%) and LOG (increased by 10.19%) models showing the most significant improvements. The feature-based domain adaptive method can alleviate the burden of collecting and labeling new data, and effectively improve the assessment performance of machine learning-based landslide susceptibility models in un-sampled areas. This is a new solution for landslide susceptibility assessment in completely “no sample” areas.

Multi-temporal analysis of landslide susceptibility in the Greater Bogor Area and its relation to land use change and rainfall variation

Landslide susceptibility in the Greater Bogor Area is a significant concern due to its hilly topography, soil types, and high rainfall. This research examines the geographical and temporal variations in landslide susceptibility and the relationship between land use change, rainfall, and landslide occurrence. Landsat 7 ETM+, CHIRPS, and DEM satellite data were used to simulate landslide susceptibility. The study used 2000, 2010, and 2020 data to examine land use and precipitation changes. The weighted overlay method created a landslide susceptibility model that considered precipitation, land use, slope, rock, and slope. The association between land use change, rainfall, and landslide susceptibility was examined using correlation analysis. According to the findings, the Greater Bogor Area is highly prone to landslides, with a growing tendency in landslide events. 22.48% of the area has a very high susceptibility classification to landslide; meanwhile, 66.46% has a high susceptibility classification. Moreover, this study also found that the land use factor correlates more positively with landslide susceptibility than the rainfall factor. Overall, this study underlines the need to take land use dynamics and rainfall patterns when assessing landslide susceptibility and the need for effective mitigation measures in the area.

Hybrid Integration of Bagging and Decision Tree Algorithms for Landslide Susceptibility Mapping

Landslides represent a significant global natural hazard, threatening human settlements and the natural environment. The primary objective of the study was to develop a landslide susceptibility modeling approach that enhances prediction accuracy and informs land-use planning decisions. The study utilized a hybrid ensemble-based methodology to improve prediction accuracy and effectively capture the complexity of landslide susceptibility patterns. This approach harnessed the power of ensemble models, employing a bagging algorithm with base learners, including the reduced error pruning decision tree (REPTree) and functional tree (FT) models. Ensemble models are particularly valuable because they combine the strengths of multiple models, enhancing the overall performance and robustness of the landslide susceptibility prediction. The study focused on Yanchuan County, situated within the hilly and gully region of China’s Loess Plateau, known for its susceptibility to landslides, using sixteen critical landslide conditioning factors, encompassing topographic, environmental, and geospatial variables, namely elevation, slope, aspect, proximity to rivers and roads, rainfall, the normalized difference vegetation index, soil composition, land use, and more. Model performances were evaluated and verified using a range of metrics, including receiver operating characteristic (ROC) curves, trade-off statistical metrics, and chi-square analysis. The results demonstrated the superiority of the integrated models, particularly the bagging FT (BFT) model, in accurately predicting landslide susceptibility, as evidenced by its high area under the curve area (AUC) value (0.895), compared to the other models. The model excelled in both positive predictive rate (0.847) and negative predictive rate (0.886), indicating its efficacy in identifying landslide and non-landslide areas and also in the F-score metric with a value of 0.869. The study contributes to the field of landslide risk assessment, offering a significant investigation tool for managing and mitigating landslide hazards in Yanchuan County and similar regions worldwide.

Modeling of landslides susceptibility prediction using deep belief networks with optimized learning rate control

To overcome critical issues in landslide susceptibility modeling, a multifactor landslide susceptibility prediction model based on deep belief networks (DBN) with optimized learning rate control (LRC-DBN) was introduced in this study. The LRC-DBN model was applied to predict landslide susceptibility in Zhidan County, Shaanxi and its performance was compared against random forest, support vector machine and logistic regression models. The results show that the LRC-DBN model achieves a maximum AUC value of 0.941, which demonstrating higher predictive performance. The interpretability of LRC-DBN reveals that the development of loess landslides is more likely in areas with elevations ranging from 894.7 m to 998.5 m, slopes ranging from 49.6° to 64°, terrain undulations spanning 31.7 m to 91.0 m, rock type T3y and terrain humidity ranging from 2.4 to 3.9. The result provides invaluable insights for local landslide prevention endeavors and can assist decision-making in urban planning.

Modelling landslide susceptibility along major transportation corridor in Darjeeling Himalayas using GIS-based MCDA approaches

Modelling landslide susceptibility along major transportation corridor in Darjeeling Himalayas using GIS-based MCDA approaches

Fast hybrid methods for modeling landslide susceptibility in Ardal County

Recently, machine learning models have received huge attention for environmental risk modeling. One of these applications is landslide susceptibility mapping which is a necessary primary step for dealing with the landslide risk in prone areas. In this study, a conventional machine learning model called multi-layer perceptron (MLP) neural network is built upon advanced optimization algorithms to achieve a firm prediction of landslide susceptibility in Ardal County, West of Iran. The used geospatial dataset consists of fourteen conditioning factors and 170 landslide events. The used optimizers are electromagnetic field optimization (EFO), symbiotic organisms search (SOS), shuffled complex evolution (SCE), and electrostatic discharge algorithm (ESDA) that contribute to tuning MLP’s internal parameters. The competency of the models is evaluated using several statistical methods to provide a comparison among them. It was discovered that the EFO-MLP and SCE-MLP enjoy much quicker training than SOS-MLP and ESDA-MLP. Further, relying on both accuracy and time criteria, the EFO-MLP was found to be the most efficient model (time = 1161 s, AUC = 0.879, MSE = 0.153, and R = 0.657). Hence, the landslide susceptibility map of this model is recommended to be used by authorities to provide real-world protective measures within Ardal County. For helping this, a random forest-based model showed that Elevation, Lithology, and Land Use are the most important factors within the studied area. Lastly, the solution discovered in this study is converted into an equation for convenient landslide susceptibility prediction.

Exploring the geomorphological adequacy of the landslide susceptibility maps: A test for different types of landslides in the Bidente river basin (northern Italy)

Landslide susceptibility modelling is a crucial tool for implementing effective strategies in landslide risk mitigation. A plethora of statistical methods is available for generating accurate prediction images; however, the reliability of these models in terms of geomorphological adequacy is often overlooked by scholars. This critical flaw may result in concealed prediction errors, undermining the trustworthiness of the obtained maps. A key aspect of evaluating the geomorphological soundness of these models lies in factor analysis, specifically considering the correlation of explanatory variables with the final susceptibility score rather than solely focusing on their impact on model accuracy.This study delves into research conducted in the Bidente river basin (Italy) that analyes results obtained from slide, flow, and complex susceptibility models using Weight of Evidence (WoE) and Multivariate Adaptive Regression Splines (MARS) statistical methods. The research critically examines each factor class's role in defining susceptibility scores for different landslide typologies. The comparison between susceptibility maps generated by WoE and MARS for each typology (slide = 0.78; flow = 0.85; complex: 0.79) (slide = 0.78; flow = 0.85; complex: 0.79)reveals good to excellent prediction skill, with MARS demonstrating a 5 % higher performance index.The study emphasises the importance of spatial relationships between variables and landslide occurrences, highlighting that individual classes of variables influence the final susceptibility score based on their combined role with other predictor classes. In particular, in this study, results highlight that lithotecnical and landform classification classes delimit the landslide domain, while topographic attributes (steepness, curvatures, SPI and TWI) modulate the score inside. The proposed approach offers insights into investigating the geomorphological adequacy of landslide prediction images, emphasising the significance of factor analysis in evaluating model reliability and uncovering potential errors in susceptibility maps.

Deep learning–based inverse analysis of GPR data for landslide hazards

In mountainous landscapes, the diverse geotechnical conditions amplify landslide susceptibility. Factors such as precipitation and seismic activity can trigger landslides, while inherent hazards such as voids, fissures, and compaction deficits jeopardize long-term slope stability. Detecting and forecasting these susceptibilities accurately is crucial. In this paper, the time-domain finite-difference approach and the gprMax software are used to conduct forward modeling of landslide susceptibility. An electrical model of subsurface aqueous structures is created, including water-filled and air-filled cavities, fracture zones, and fault lines. The distinctive radar signal responses within these environments are examined, and a dataset of B-scan images associated with their electrical models is constructed. By employing deep learning algorithms and the robust nonlinear mapping ability of convolutional neural networks in the Pix2Pix generative adversarial network, we accelerate the intelligent inversion of the geological radar data on landslide susceptibility. This innovative approach effectively reconstructs hazard models, offering a reliable basis for interpretation of radar signals.