Landslide Susceptibility Analysis Research Articles

Enhancing Seismic Landslide Susceptibility Analysis for Sustainable Disaster Risk Management through Machine Learning

The accuracy of Seismic Landslide Susceptibility Maps (SLSMs) is imperative for the prevention of seismic landslide disasters. This study enhances the precision of SLSMs by integrating nine distinct machine learning methodologies with the GeoDetector version 0.0.4 tool to filter both numerical and physical factors contributing to landslide susceptibility. The dataset comprises 2317 landslide instances triggered by the 2013 Minxian Ms = 6.6 earthquake, from which redundant factors were pruned using the Recursive Feature Elimination technique. Subsequent evaluations of the optimized factors, both individually and in combination, were conducted through Frequency Ratio analysis and Factor Interaction assessment. The study juxtaposes the Area Under the Receiver Operating Characteristic Curve (AUC) and the accuracy of nine machine learning models before and after factor optimization. The findings indicate an increase in AUC from a maximum of 0.989 to 0.992 in the Random Forest model, and an 8.37% increase in AUC for the SVM model, signifying a notable enhancement in the stability across all models. The establishment of the SLSM notably elevated the frequency ratio in high-risk zones from 50.40 to 85.14, underscoring the efficacy of combining machine learning and detector optimization techniques in sustainable practices. This research proposes a universal framework aimed at eliminating redundancy and noise in SLSMs and hazard risk assessments, thereby facilitating sustainable geological disaster risk management.

Analysis of landslide susceptibility and potential impacts on infrastructures and settlement areas (a case from the southeastern region of Türkiye)

Landslides have harmful effects not only on buildings but also on infrastructure and the natural environment. While they are typically triggered by natural events, such as heavy rainfalls and earthquakes, landslides can also be induced by anthropogenic activities, such as excavation and blasting. In certain regions, gigantic paleo-landslides exist, but triggering them is extremely difficult. However, triggering secondary landslides in gigantic paleo-landslides is relatively easy compared to the main corpus. The main purpose of this study was to produce a susceptibility map in a region in southeastern Türkiye and to discuss the impact of petroleum seismological investigation concerning the trigger of the landslides. For this purpose, a landslide inventory was compiled using geospatial data sets and field observations and used for landslide susceptibility mapping with the Random Forest algorithm. The accelerations sourced from blasting were also measured and the run-out distances were determined. A run-out distance map was produced using inverse distance weights. The study presents comprehensive insights by integrating a landslide susceptibility map and run-out distance map. It evaluates the impact of blasting on landslides through in-situ measurements and slope stability analyses. Findings indicate that no triggering effect on landslides was observed if the dynamite quantity remains below 4 kg and the blasting distance exceeds 10 m from the landslide.

Utilization of Frequency Ratio and Logistic Regression Model for Landslide Susceptibility Mapping in Bogor Area

Java Island holds the highest record of landslide events in Indonesia. In 2021, the Bogor area, consisting of the city and regency of Bogor, recorded the highest number of landslides. These events further impact the fatalities, damage, and loss to society. Landslide mitigation should be considered to reduce the risk caused by landslide hazards. In this regard, a landslide susceptibility analysis is one of the fundamental steps in mitigation measures that can support policymakers in response to landslide disaster risk reduction. The location of landslide possibilities can be identified by mapping landslide susceptibility. Therefore, this study aims to produce a landslide susceptibility map (LSM) using a statistical frequency ratio method and logistic regression. The number of landslide inventories used in the model is about 822 events. To apply the model, the present study evaluates 13 influencing factors consisting of elevation, slope angle, slope aspect, slope curvature, Topographic Wetness Index (TWI), distance to river, lithological, distance to fault, soil type, annual rainfall, Normalized Difference Vegetation Index (NDVI), land use land cover (LULC), and road distance. The model performance is further evaluated using Area Under the ROC Curve (AUC). The frequency ratio (FR) and logistic regression (LR) models produce satisfactory results and have high predictions of future landslide occurrences with a score of 0.8317 and 0.8817, respectively.

Optimizing landslide susceptibility mapping using machine learning and geospatial techniques

Landslides present a substantial risk to human lives, the environment, and infrastructure. Consequently, it is crucial to highlight the regions prone to future landslides by examining the correlation between past landslides and various geo-environmental factors. This study aims to investigate the optimal data selection and machine learning model, or ensemble technique, for evaluating the vulnerability of areas to landslides and determining the most accurate approach. To attain our objectives, we considered two different scenarios for selecting landslide-free random points (a slope threshold and a buffer-based approach) and performed a comparative analysis of five machine learning models for landslide susceptibility mapping, namely: Support Vector Machine (SVM), Logistic Regression (LR), Linear Discriminant Analysis (LDA), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The study area for this research is an area in Polk County in Western North Carolina that has experienced fatal landslides, leading to casualties and significant damage to infrastructure, properties, and road networks. The model construction process involves the utilization of a dataset comprising 1215 historical landslide occurrences and 1215 non-landslide points. We integrated a total of fourteen geospatial data layers, consisting of topographic variables, soil data, geological data, and land cover attributes. We use various metrics to assess the models' performance, including accuracy, F1-score, Kappa score, and AUC-ROC. In addition, we used the seeded-cell area index (SCAI) to evaluate map consistency. The ensemble of the five models using Weighted Average produces outstanding results, with an AUC-ROC of 99.4% for the slope threshold scenario and 91.8% for the buffer-based scenario. Our findings emphasize the significant impact of non-landslide random sampling on model performance in landslide susceptibility mapping. Furthermore, by optimally identifying landslide-prone regions and hotspots that need urgent risk management and land use planning, our study demonstrates the effectiveness of machine learning models in analyzing landslide susceptibility and providing valuable insights for informed decision-making and disaster risk reduction initiatives.

Application of machine learning in the assessment of landslide susceptibility: A case study of mountainous eastern Mediterranean region, Syria

Landslide is a considerable geomorphological risk in terrain systems worldwide. Advanced techniques present a unique tool for predicting landslide susceptibility with unbiased and precise outputs. However, the application of this tool to analyze landslide susceptibility in the eastern Mediterranean landscape is still not sufficiently understood. This study aimed to assess the implementation of three machine learning (ML) algorithms, i.e., support vector machine (SVM), random forest (RF) and extreme gradient boost (XGBoost), in landslide susceptibility mapping in the mountainous area of western Syria. In this regard, 200 landslide events were inventoried from historical data, aerial images and conducted fieldworks. Sixteen triggering factors were selected according to the literature and geographical features (Monsoon period). The receiver operating characteristic (ROC) outcomes revealed that the RF achieved better performance with an area under curve (AUC) of 0.96, pursued by XGBoost and SVM with AUC of 0.94 and 0.90, respectively. This assessment presents an essential understanding of the effective implementation of ML in landslide assessment in the mountainous region of the eastern Mediterranean. We emphasized, hence, that the RF algorithm has the most robust performance of landslide susceptibility prediction in the western Syria. Moreover, the outputs of this study will provide local decision-makers with insights to produce regional management strategies for the landslide, especially after the Syrian war phase.

Landslide susceptibility mapping of the main boundary thrust region in Thungsingdanda-Bandipur section of Nawalparasi and Palpa Districts, Gandaki and Lumbini Provinces, Nepal

This research assesses the results of a landslide susceptibility analysis employing frequency ratios (FR). It was conducted in collaboration between CNES/Airbus and Maxar Technologies using Google Earth. Landslides in the Thungsingdanda-Bandipur area were identified through imagery with a 50 cm spatial resolution. A comprehensive dataset for training and testing was established based on the landslide inventory. Nine causative variables: slope, aspect, relief, distance from the stream, distance from the road, curvature, distance from the thrust, geology, and land use were used. FR ratings were assigned to these causative variables based on training events. The resultant landslide susceptibility map was generated by integrating causative variables with their respective FR ratings. The validation rate, determined using the ROC-AUC curve, was found to be 82.2 percent. Notably, distance from the thrust (MBT), land use, and distance from the road emerged as the more influential factors among the nine causative variables in landslide occurrences.

Comparison of Statistical and Machine-Learning Model for Analyzing Landslide Susceptibility in Sumedang Area, Indonesia

Landslides have produced several recurrent dangers, including losses of life and property, losses of agricultural land, erosion, population relocation, and others. Landslide mitigation is critical since population and economic expansion are rapidly followed by significant infrastructure development, increasing the risk of catastrophes. At an early stage in landslide-disaster mitigation, landslide-risk mapping must give critical information to help policies limit the potential for landslide damage. This study will utilize the comparative frequency ratio (FR) and random forest (RF) techniques; they will be utilized to properly investigate the distribution of flood vulnerability in the Sumedang area. This study has identified 12 criteria for developing a landslide-susceptibility model in the research region based on the features of past disasters in the research area. The FR and RF models scored 88 and 81% of the AUC value, respectively. Based on the McNemar test, the FR and RF models featured the same performance in determining the landslide-vulnerability level performances in Sumedang. They performed well in assessing landslides in the research region; therefore, they may be used as references in landslide prevention and references in future regional development plans by the stakeholders.

Enhancing co-seismic landslide susceptibility, building exposure, and risk analysis through machine learning

Landslides are devastating natural disasters that generally occur on fragile slopes. Landslides are influenced by many factors, such as geology, topography, natural drainage, land cover, rainfall and earthquakes, although the underlying mechanism is too complex and very difficult to explain in detail. In this study, the susceptibility mapping of co-seismic landslides is carried out using a machine learning approach, considering six districts covering an area of 12,887 km2 in Nepal. Landslide inventory map is prepared by taking 23,164 post seismic landslide data points that occurred after the 7.8 MW 2015 Gorkha earthquake. Twelve causative factors, including distance from the rupture plane, peak ground acceleration and distance from the fault, are considered input parameters. The overall accuracy of the model is 87.2%, the area under the ROC curve is 0.94, the Kappa coefficient is 0.744 and the RMSE value is 0.358, which indicates that the performance of the model is excellent with the causative factors considered. The susceptibility thus developed shows that Sindhupalchowk district has the largest percentage of area under high and very high susceptibility classes, and the most susceptible local unit in Sindhupalchowk is the Barhabise municipality, with 19.98% and 20.34% of its area under high and very high susceptibility classes, respectively. For the analysis of building exposure to co-seismic landslide susceptibility, a building footprint map is developed and overlaid on the co-seismic landslide susceptibility map. The results show that the Sindhupalchowk and Dhading districts have the largest and smallest number of houses exposed to co-seismic landslide susceptibility. Additionally, when conducting a risk analysis based on susceptibility mapping, as well as considering socio-economic and structural vulnerability in Barhabise municipality, revealed that only 106 (1.1%) of the total 9591 households, were found to be at high risk. As this is the first study of co-seismic landslide risk study carried out in Nepal and covers a regional to the municipal level, this can be a reference for future studies in Nepal and other parts of the world and can be helpful in planning development activities for government bodies.

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.

Physics-informed optimization for a data-driven approach in landslide susceptibility evaluation

Landslide susceptibility mapping is an integral part of geological hazard analysis. Recently, the emphasis of many studies has been on data-driven models, notably those derived from machine learning, owing to their aptitude for tackling complex non-linear problems. However, the prevailing models often disregard qualitative research, leading to limited interpretability and mistakes in extracting negative samples, i.e. inaccurate non-landslide samples. In this study, Scoops 3D (a three-dimensional slope stability analysis tool) was utilized to conduct a qualitative assessment of slope stability in the Yunyang section of the Three Gorges Reservoir area. The depth of the bedrock was predicted utilizing a Convolutional Neural Network (CNN), incorporating local boreholes and building on the insights from prior research. The Random Forest (RF) algorithm was subsequently used to execute a data-driven landslide susceptibility analysis. The proposed methodology demonstrated a notable increase of 29.25% in the evaluation metric, the area under the receiver operating characteristic curve (ROC-AUC), outperforming the prevailing benchmark model. Furthermore, the landslide susceptibility map generated by the proposed model demonstrated superior interpretability. This result not only validates the effectiveness of amalgamating mathematical and mechanistic insights for such analyses, but it also carries substantial academic and practical implications.

Landslide susceptibility analysis using random forest model with SMOTE-ENN resampling algorithm

Landslide is one of the natural disasters that cause property damages and human injuries. Landslide hazard predictions are crucial measures to reduce the damages and losses. One of the effective approaches in landslide prediction is landslide susceptibility analysis (LSA). In this article, LSA is carried out on the study area, Penang Island. The imbalanced landslide dataset is the most important issue to be solved in this article, four resampling methods were compared for the training set using random forest (RF) as the basic model. To enhance the credibility of the results, the experiments replicate 10 times, and McNemar’s test was applied to analyse statistical significance of classifier performances for the LSA. The results indicated that the differences between the methods were statistically significant; RF combined with the synthetic minority oversampling technique-edited nearest neighbour (SMOTE-ENN) resampling method proposed in this paper has positive effect in LSA as compared with the other resampling methods. The RF and SMOTE-ENN combined model for the LSA using the min–max normalization method achieved a recall of 0.844 and an F2-score of 0.756. The SMOTE-ENN method had a significant impact on the LSA of the imbalanced data in the study area.

Landslide susceptibility zonation using the analytical hierarchy process (AHP) in the Great Xi’an Region, China

This study aims to delineate landslide susceptibility maps using the Analytical Hierarchy Process (AHP) method for the Great Xi’an Region, China, which is a key planning project for urban construction in Shaanxi Province, China from 2021 to 2035. Multiple data as elevation, slope, aspect, curvature, river density, soil, lithology, and land use have been considered for delineating the landslide susceptibility maps. Spatially thematic layers and distributed maps of all the aforementioned parameters were created in a GIS environment. Determine the relative importance of these thematic layers in the occurrence of landslides in the study area concerning historical landslide data to assign appropriate weights. Landslide sensitivity maps were generated by a weighted combination in a GIS environment after being analyzed by the AHP method. The sensitivity maps were categorized as “very high (11.06%), high (19.41%), moderate (23.03%), low (28.70%), and very low (17.80%)”. Overlay analysis of the test data with the LSM showed that the moderate to very high landslide susceptibility zones were able to contain 82.58% of the historic landslides. The results of the study help determine the landslide-prone areas in the area and provide a reference for subsequent construction. In addition, the analysis of landslide susceptibility in the area contributes to the study of landslides in similar loess sites.

Landslide Susceptibility Analysis of Yalova-Çınarcık Region with Logistic Regression, Frequency Ratio, and ArcGIS Pro Suitability Model

Bu çalışmada Türkiye’nin batısında yer alan Yalova-Çınarcık bölgesinde, yaklaşık 11 km2 olan inceleme alanında heyelan duyarlılık analizi yapılmıştır. Bölgede geniş yayılımlı 20 heyelan bölgesi incelenmiştir. Mantıksal Regresyon, Frekans Oranı ve ArcGIS Pro Uygunluk Modeli ile heyelan duyarlılık analizi yapılmıştır. Verilerin %80’i analiz, %20’si test için kullanılmıştır. Analizin doğruluğunu test etmek için Alıcı İşletim Karakteristik (Receiver Operating Charasteristic-ROC) eğrisi ve Eğrinin Altında Kalan Alan (Area Under the Curve-AUC) kullanılmıştır. Yapılan analizler sonucunda Mantıksal Regresyon yöntemine göre inceleme alanının %5.41’i çok düşük, %10.32’si düşük, %31,22’si orta, %24,98’i yüksek ve %28,05’i çok yüksek heyelan duyarlılık sınıfındadır ve AUC sonucu ise %78,8’dir. Frekans Oranı için ise inceleme alanının %30,8’i çok düşük, %14,48’i düşük, %4,5’i orta, %24,02’si yüksek ve %26,2’si çok yüksek heyelan duyarlılık sınıfında olup AUC sonucu %64,4’tür. ArcGIS Pro Uygunluk Modeli için ise %4,42’si çok düşük, %20,57’si düşük, %27,9’u orta, %23,42’si yüksek ve %23,67’si çok yüksek ve AUC değeri %69,7’dir. Bu çalışmada elde edilen duyarlılık analizi verileri ile yüksek ve çok yüksek duyarlılık sınıfındaki bölgeler için gerekli önlemlerin ve bölgede yapılacak arazi planlaması için bu sonuçların dikkate alınması önerilmiştir.

Landslide susceptibility analysis in the Bhilangana Basin (India) using GIS-based machine learning methods

Landslides are frequent natural hazards in mountainous regions, and harshly upset people's lives and livelihoods. In the present study, we have carried out an analysis of seven GIS-based machine-learning techniques; and asses their performance for landslide susceptibility mapping (LSM) in the Bhilangana Basin, Garhwal Himalaya. A landslide inventory consisting of 423 polygons was prepared using repeated field investigations, and multi-dated satellite images for the periods between 2000 and 2022. The landslide dataset was classified into two groups: training (70%) and test dataset (30%), and 12 predictive variables were used for the LSM. The methods used to produce LSM are boosted regression tree (BRT), Fisher discriminant analysis (FDA), generalized linear model (GLM), multivariate adaptive regression splines (MARS), model-architect analysis (MDA), random forest (RF) and support vector machine (SVM). The sensitivity and performance of these models to predict landslide susceptible areas were carried out using the area under the curve (AUC) method. The RF model (AUC = 0.988) has given the highest precision indicating the best performance. Though MARS (0.974), SVM (0.965) and MDA (0.952) models have also performed adequately for the LSM (all have AUC values above 0.95), however, it is recommended that the RF model is highly suitable for LSM in the mountainous region.

Landslide susceptibility mapping of the Main Boundary Thrust region in Mandre - Khursanibari section of Arghakhanchi and Palpa Districts, Lumbini Province, Nepal

The Mandre-Khursanibari section of Arghakhanchi and Palpa districts consists of numerous landslides, small to large. Prospecting weak geological sections like the location of the Main Boundary Thrust (MBT) and inherently weak lithological settings in addition to other factors are the main objectives of the present research. In this study, the results of the landslide susceptibility analysis using frequency ratios (FR) are assessed. The Mandre-Khursanibari segment was subjected to landslide detection using imagery (Google Earth) with a spatial resolution of 50 cm. The landslide inventory was used to construct training and testing data. Based on topographic, geological, and land-use maps, nine contributing variables were identified. The FR ratings were established using the contributing elements and training data. The map illustrating landslide risk was produced by integrating the influencing components that determined FR ratings. The ROC-AUC curve shows a validation rate of 82.2 % in the present model of LSI. The three most important elements in the occurrence of the landslide, out of the nine potential causes, are distance from the thrust (MBT), land use, and distance from the road. However, the role of adverse lithological setting is found to be a minor in many sections of this region. The MBT is one of the main causes of landslides in this area.

Landslide Risk Assessment and Preventive Measures of Selected Locations in the Rangamati District, Bangladesh

Detecting landslides and unstable slopes is one of the most crucial responsibilities in the emergency response to resist landslides. Having a wide range of hilly terrines in the southeast region of Bangladesh, the risk of landslide disasters is becoming a critical issue. In Chittagong, especially in the Rangamati hill tracts, there have been several losses of life and property due to landslides in the recent past. This research attempts to evaluate the landslide risk in Rangamati hill tracts and provide suggestions to mitigate the landslide hazard by modifying the hill slope. Soil specimens from different hill locations were collected from three areas in the Rangamati district. Several laboratory experiments were conducted to determine the soil properties, and 2D slope stability analysis using Bishop's simplified method was used to evaluate the landslide potential. Different preventative measures, for example, soil nailing, anchors, and cutting slopes like stairs, are also implemented to mitigate the landslide potential by increasing the slope stability was assessed and suggested. Weighted Overlay Model (W.O.M.) was implemented for the Landslide Susceptibility Analysis in ArcGIS to confirm the potential hazard in the study areas, and hazard maps were suggested based on the slope stability results and current slopes in Rangamati. The slope stability analysis of the three spots showed that spot 3 is the most vulnerable spot, which had a low factor of safety value. Even with different mitigation techniques, spot 3 showed a lower factor of safety value, which was verified with the Weighted Overlay Method. It was also seen that among the mitigation techniques, anchoring the slopes is the most effective one that drastically increases the factor of safety value.

A REVIEW OF STATISTICAL APPROACHES USED FOR LANDSLIDE SUSCEPTIBILITY ANALYSIS WITH THE HELP OF REMOTE SENSING AND GIS TECHNOLOGY

One of the most significant environmental risks is landslides. It might happen due to human action or natural occurrence and have significant social, economic, and environmental repercussions. The danger of landslides occurring in a certain area based on regional topographical features is known as landslide susceptibility. Numerous articles evaluating landslide susceptibility have been written since the middle of the seventies utilizing a variety of techniques and methodologies in diverse geographical and environmental situations.To critically review this literature, major factors that are considered for landslide susceptibility, and the models that are used for landslide susceptibility analysis. Then these data are represented in a graphical visualization form.Landslide susceptibility zoning, The goal of the current study, which was undertaken as a review, was to provide a critical analysis of statistical methods used for landslide susceptibility modelling and associated terrain zonation from 2010 to 2023.There has been an increase in the number of publications from 2019 onwards on the topic of landslide susceptibility. In 20.8% of the studies, the FR model and LR model has been chosen as the most popular approach for determining landslide vulnerability. Other then Logistic regression and Frequency ratio model, other models like Fuzzy, WoE, ANN, SVM and RF are also popular for landslide susceptibility. As the technology in the field of GIS&RS is updating day to day and recent policy developments, are significant factors in boosting interest in landslide susceptibility research.

Development of an integrated model for assessing landslide susceptibility on vegetated slopes under random rainfall scenarios

Physically-based landslide susceptibility analysis has been extensively employed to predict the likelihood of landslides owing to its remarkable predictive capability. However, due to an insufficiently comprehensive analysis of the vegetation-disaster connection, this approach may face limitations in its application to regions where there is significant variation in vegetation diversity and topography. An integrated model was thus proposed for predicting landslide susceptibility with the consideration of the positive and negative effects of vegetation on slope stability. However, to accurately implement the slope failure process under the influence of vegetation, it is important to have a high temporal resolution rainfall scenario for simulating the interception process of vegetation crowns on rainfall. Analysis of vegetation hydrological processes is associated with difficulties in a regional area because of limited data availability. The stochastic simulation method for extreme rainfall scenarios, adopted in this study, is known to be effective in dealing with uncertainty caused by insufficient data. The method, which comprises the Gumbel model and Bounded Random Cascade Model (BRCM), was used to overcome the difficulties in integrating the comprehensive effects of vegetation, the results of which provide refined rainfall scenarios for landslide susceptibility prediction from the perspective of the failure mechanism of vegetated slopes. The application of the proposed method for landslide susceptibility zoning was validated using a confusion matrix and ROC curve analysis in a practical case. Results showed that the method performed effectively and reliably. Furthermore, this study investigated the influence of different extreme rainfall scenarios on slope stability. Results revealed that as the return period of extreme rainfall increased from 50 to 150 years, the overall proportion of susceptible areas for different rainfall durations exhibited an upward trend. Additionally, the study found that increasing vegetation biomass had a positive impact on slope stability in the study area. The findings of this study are significant for disaster prevention and mitigation in mountainous regions, providing scientific support for risk management strategies.

Analysis of Landslide Susceptibility Using Frequency Ratio Methods in the Lisu Watershed, Barru Regency

Barru Regency is an area with a relatively high frequency of landslides according to BNPB data for 2015. This can be seen in several incidents from 2017 to 2021. The purpose of this research is to identify and determine the level of vulnerability of landslides that occur in an area by utilizing the method Frequency Ratio. The Lisu watershed study area is a research study because it is included in the largest local watershed in Barru Regency. This study uses landslide occurrence point data by including nine factors that cause landslides such as land cover, slope, slope aspect, elevation, rainfall, curvature, distance from river, distance from fault, and lithology. These nine factors are divided into five classes, namely very low, low, medium, high, and very high. The results of the analysis show that the AUC model success rate and prediction accuracy are 0.80 and 0.83. The very high vulnerability to landslides is spread over the Tanete Riaja and Pujananting Districts. This indicates that the frequency ratio method is appropriate as a basis for analyzing the level of landslide vulnerability in the Lisu watershed.

Modelling rainfall-induced landslides at a regional scale, a machine learning based approach

AbstractIn Italy, rainfall represents the most common triggering factor for landslides; thus, many Italian Regional Departments of Civil Protection are setting up warning systems based on rainfall recordings. Common methods are mainly based on empirical relationships that provide the rainfall thresholds above which the occurrence of landslide phenomena is likely to be expected. In recent years, the use of machine learning approaches has gained popularity in landslide susceptibility analysis and prediction. To support the operational early warning system of Liguria Civil Protection Department for landslides hazard, we propose the implementation of a polynomial Kernel regularized least squares regression (KRLS) algorithm, for predicting the daily occurrence of shallow landslides in the five Alert Zones in Liguria (North Western Italy). The model provides an estimate of the number of landslides associated with the set of three different hydrological features, also used for the Hydrological Assessment procedure: the soil moisture, the accumulated precipitation over 12 h and the precipitation peak over 3 h. Results of the model are converted to an Alert Scenario of landslide occurrence, based on the magnitude of the expected event and identified according to the National and Regional legislation (Regional Civil Protection guidelines D.G.R. n. 1116, 23/12/2020). The performance of the predictive model (e.g. accuracy of 93%) is deemed satisfactory and the methodology is considered a valuable support to the operational early warning system of Liguria Civil Protection Department. The choice of predictive variables allows, in future development, the values obtained from historical data to be replaced by those obtained from meteorological forecast models, introducing the use of the developed model in the operational forecasting chain.