Landslide Inventory Research Articles

A regional scale coseismic landslide analysis framework: Integrating physics-based simulation with flexible sliding analysis

This paper describes a framework for regional scale coseismic landslide evaluation that combines physics-based wave propagation simulation at a regional scale, with flexible sliding analysis at a site scale. The physics-based simulation incorporates fault rupture process, complex topography and dynamic site response. The sliding displacements of flexible masses are calculated by integrating seismic parameter k obtained from the physics-based simulation over seismic resistance.The framework is applied to the case study of coseismic landslides during the 2016 Mw 7.0 Kumamoto earthquake in Japan, which has well documented fault mechanism, geologic information and landslide inventory. The performance of the model prediction is evaluated by receiver operating characteristic (ROC) analysis. This study highlights the near-fault effect and soil nonlinear effect on landslide distribution, and it is demonstrated that the landslide prediction can be notably improved with the consideration of topographic amplification of ground motions. Empirical correlations between topographic amplification of key intensity measures and parameterized topographic features are developed. Overall, the simulation captures 58% of observed landslides in the inventory (using a displacement threshold of 15 cm), showing the proposed framework is a promising tool for regional coseismic landslide analysis.

Analysis of spatial distribution of landslides triggered by the Ms 6.8 Luding earthquake in China on September 5, 2022

BackgroundOn September 5, 2022, an Ms 6.8 earthquake occurred in Luding County, Ganzi Tibetan Autonomous Prefecture, Sichuan, China. The casualties and economic losses caused by the earthquake are huge. Most of the landslides triggered by this earthquake are small and medium-sized rock collapses and destructive debris flows, with a small number of large-scale landslides.ResultsThere are 5007 coseismic landslides in the Luding earthquake VII-degree area and above, with a total area of 17.36 km2. The landslides are generally distributed along the NW-SE direction. The highest landslide area density is 13.8%, and the highest point density of the landslide is 35.73 km2. High-density area is mainly concentrated in the IX-degree area and the northeast side of the seismogenic fault. Coseismic landslides are more likely to develop in the area with the slope more than 40°, the slope direction of 67.5-112.5 degree, and vegetation coverage of 40–50%. More landslides are developed in granite areas and forest areas. The closer distance to active faults, the more the coseismic landslides develop. The correlation between coseismic landslide development and the distance from the active faults is better than that between coseismic landslide development and the distance from the seismogenic faults.ConclusionThe landslide database used in this paper is the most perfect at present, and the research results have also been verified by fieldwork. This is also the first applied study of this landslide inventory, which indirectly confirmed the accuracy of the inventory. The results obtained in the manuscript will provide an important guideline for futuredisaster prevention and mitigation in southwest China.

P-band SAR for ground deformation surveying: Advantages and challenges

Global success of utilizing X/C/L-band InSAR (Interferometric Synthetic Aperture Radar) to survey ground deformation over non-forested terrain in the past two decades, has raised interest in monitoring forested lands, where relatively short-wavelength X/C/L SAR acquisitions often experience strong decorrelation and downgraded InSAR quality. To address this challenge, we considered the long-wavelength P-band SAR and conducted a large-area experiment over diverse terrains of the U.S. West Coast to comprehensively assess P-band SAR's capability for ground deformation surveying. Our results show that P-band InSAR observations greatly outperformed L-band data for identifying ground deformation within forested regions and for measuring spatially high-gradient displacements, such as for slow-moving landslides. Over the entire study area, P-band InSAR helped to discover >200 new landslides that were missing from existing landslide inventories. It also demonstrated high capability of penetrating through shallow snowpack to collect SAR signals from the ground surface beneath. However, P-band data manifested lower sensitivity to subtle deformation, as expected theoretically, and encountered coherence loss resulting from heavy snowpack. Overall, P-band SAR demonstrated to be a highly effective tool for discovering deformation beneath dense forest canopies and for quantifying spatially high-gradient displacements. These findings provide an experimental basis for planning future satellite and airborne P-band SAR missions to enhance the capability to monitor changes of the Earth's surface.

Assessing uncertainties in landslide susceptibility predictions in a changing environment (Styrian Basin, Austria)

Abstract. The assessment of uncertainties in landslide susceptibility modelling in a changing environment is an important, yet often neglected, task. In an Austrian case study, we investigated the uncertainty cascade in storylines of landslide susceptibility emerging from climate change and parametric landslide model uncertainty. In June 2009, extreme events of heavy thunderstorms occurred in the Styrian Basin, triggering thousands of landslides. Using a storyline approach, we discovered a generally lower landslide susceptibility for the pre-industrial climate, while for the future climate (2071–2100) a potential increase of 35 % in highly susceptible areas (storyline of much heavier rain) may be compensated for by much drier soils (−45 % areas highly susceptible to landsliding). However, the estimated uncertainties in predictions were generally high. While uncertainties related to within-event internal climate model variability were substantially lower than parametric uncertainties in the landslide susceptibility model (ratio of around 0.25), parametric uncertainties were of the same order as the climate scenario uncertainty for the higher warming levels (+3 and +4 K). We suggest that in future uncertainty assessments, an improved availability of event-based landslide inventories and high-resolution soil and precipitation data will help to reduce parametric uncertainties in landslide susceptibility models used to assess the impacts of climate change on landslide hazard and risk.

Landslide susceptibility assessment on a large scale in the Podsljeme area, City of Zagreb (Croatia)

ABSTRACT The study presents a landslide susceptibility assessment on a large scale in the City of Zagreb (Croatia). The susceptibility analysis was performed using the Weight of Evidence model in the pilot area (21 km2) and applying the obtained weight values for each class of conditioning factors in the study area (130 km2). The input data were LiDAR-based landslide inventory and six conditioning factors derived from 5 m LiDAR DTM, 5 m SfM DEM, and geological and land-use maps. The validation of the susceptibility assessment for the study area was evaluated with a ROC curve, which showed a high prediction rate (AUC = 84.4%), similar to the prediction rate for the pilot area (AUC = 86.9%). Based on the results, it can be concluded that the proposed method for large-scale landslide susceptibility assessment, where susceptibility conditions are defined in smaller pilot areas, can be applied to larger research areas with similar geomorphological and geological conditions.

Using DInSAR to inventory landslide geological disaster in Bijie, Guizhou, China

Landslides are very complicated natural phenomena that create significant losses of life and assets throughout China. However, previous studies mainly focused on monitoring the development trend of known landslides in small areas, and few studies focused on the identification of new landslides. In addition, karst areas, where the vegetation is dense, the mountains are high, the slopes are steep, and the time incoherence is serious, have difficulty in tracking Differential Interferometric Synthetic Aperture Radar (DInSAR) landslides. Therefore, based on DInSAR technology, we use ALOS-2 PALSAR data to conduct continuous monitoring of existing hazards and identify new geological hazards in karst areas. The major results are as follows: 1) From June 11 to 6 August 2017, it was discovered that a hidden point of landslides occurred on the 420 m northwest mountain near the town of Zongling. It was determined that the landslide hidden point had been slipping for two consecutive years, with an average slip of 6.0 cm. From 4 September 2016 to 22 January 2017, undiscovered hidden points in the landslide account were found in Yinjiazhai. On 13 September 2016 and 22 November 2016, the discovered potential hazards in the landslide log book were the mountain hazards in southwestern Shiping village, and the deformation was 7.8 cm. 2) The DInSAR monitoring results from September to November 2016 showed that large deformations occurred in the landslide area of Shiping village. During a field visit, large cracks on the surface were found. The length of surface cracks in the southwest direction of Shiping village was 2.8 m. On 13 July 2017, Shiping collapsed as a result of the collapse of the mountainous area where the disaster occurred. The average slope of the landslide in the landslide area was approximately 65°, the height was 95 m, the length and width were 150 m and 25 m, respectively, and the thickness was 5 m. The method has shown great potential in precisely identifying some new geological hazards sites, as well as tracking and monitoring the potential hazards of geological disasters listed on the landslide account.

Increasing landslide activity in the Taxkorgan River Basin (eastern Pamirs Plateau, China) driven by climate change

Global warming promotes glacier retreat, snow melting, and permafrost thawing, thereby increasing landslide activity in alpine mountain regions. However, our understanding of the effects of climate change on landslides is restricted by the sparse nature of landslide records. In this study, taking the Taxkorgan River basin in the eastern Pamirs as the study area, we assessed the interaction between landslides and climate change over the past 20 years using a reconstructed landslide inventory and a set of downscaled meteorological data, and we projected the future impacts of climate change on landslide activity. From 2000 to 2019, the number of landslides increased exponentially under global warming. Especially in 2000 and 2014, the abrupt increases in temperature and precipitation caused a more significant increase in the number of landslides. Ninety-four percent of the landslides occurred in the warm season (April to October), which is attributed to the diminishing snow cover in the warm season and the increase in the annual snow cover variation. Spatially, the increase in the number of landslides with elevation was due to the increase in the rate of temperature rise, suggesting that the high-elevation region (4500 m above sea level) responds more significantly to climate change and is more susceptible to landslides. The future climate is predicted to exhibit a warming and wetting trend, which will likely induce more frequent landslides for some time. We suggest that in alpine mountain areas, there is an urgent need to improve the comprehensive ground observation network and reveal the underlying relationship between the variable climate and landslides using multiple datasets, which would contribute to the accurate assessment of the risks posed by landslides induced by climate change and the adequate management of this risk under the warming climate in the future.

A Procedure for the Quantitative Comparison of Rainfall and DInSAR-Based Surface Displacement Time Series in Slow-Moving Landslides: A Case Study in Southern Italy

Earth observation data are useful to analyze the impact of climate-related variables on geomorphological processes. This work aims at evaluating the impact of rainfall on slow-moving landslides, by means of a quantitative procedure for identifying satellite-based displacement clusters, comparing them with rainfall series, and applying statistical tests to evaluate their relationships at the regional scale. The chosen study area is the Basento catchment in the Basilicata region (southern Italy). Rainfall series are gathered from rain gauges and are analyzed to evaluate the presence of temporal trends. Ground displacements are obtained by applying the P-SBAS (Parallel Small BAseline Subset) to three datasets of Sentinel-1 images: T146 ascending orbit, and T51 and T124 descending orbits, for the period 2015–2020. The displacement series of the pixels located in areas mapped as landslides by the Italian Landslide Inventory and sited within rain gauge influence regions (defined as 10 km circular buffers) are studied. Those displacement series are analyzed and compared to the rainfall series to search for correlations, by employing statistical and non-parametric tests. In particular, two landslides are selected and investigated in detail. Significant results were obtained for the T124 descending orbit for both landslides, for a 3-day cumulative rainfall and a 7-day delay of the slope response. Challenges in the whole procedure are highlighted and possible solutions to overcome the raised problems are proposed. Given the replicability of the proposed quantitative procedure it might be applied to any study area.

Generating multi-temporal landslide inventories through a general deep transfer learning strategy using HR EO data

Mapping of landslides over space has seen an increasing attention and good results in the last decade. While current methods are chiefly applied to generate event-inventories, whereas multi-temporal (MT) inventories are rare, even using manual landslide mapping. Here, we present an innovative deep learning strategy which employs transfer learning that allows for the Attention Deep Supervision Multi-Scale U-Net model to be adapted for landslide detection tasks in new areas. The method also provides the flexibility of re-training a pretrained model to detect both rainfall- and earthquake-triggered landslides on new target areas. For the mapping, we used archived Planet Lab remote sensing images spanning a period between 2009 till 2021 with spatial resolution of 3–5 m to systematically generate MT landslide inventories. When we examined all cases, our approach provided an average F1 score of 0.8 indicating that we successfully identified the spatiotemporal occurrences of landslides. To examine the size distribution of mapped landslides we compared the frequency-area distributions of predicted co-seismic landslides with manually mapped products from the literature. Results showed a good match between calculated power-law exponents where the difference ranges between 0.04 and 0.21. Overall, this study showed that the proposed algorithm could be applied to large areas to generate polygon-based MT landslide inventories.

A Comparative Assessment of Sampling Ratios Using Artificial Neural Network (ANN) for Landslide Predictive Model in Langat River Basin, Selangor, Malaysia

Landslides have been classified as the most dangerous threat around the world, causing huge damage to properties and loss of life. Increased human activity in landslide-prone areas has been a major contributor to the risk of landslide occurrences. Therefore, machine learning has been used in landslide studies to develop a landslide predictive model. The main objective of this study is to evaluate the most suitable sampling ratio for the predictive landslide model in the Langat River Basin (LRB) using Artificial Neural Networks (ANNs). The landslide inventory was divided randomly into training and testing datasets using four sampling ratios (50:50, 60:40, 70:30, and 80:20). A total of 12 landslide conditioning factors were considered in this study, including the elevation, slope, aspect, curvature, topography wetness index (TWI), distance to the road, distance to the river, distance to faults, soil, lithology, land use, and rainfall. The evaluation model was performed using certain statistical measures and area under the curve (AUC). Finally, the most suitable predictive model was chosen based on the model validation results using the compound factor (CF) method. Based on the results, the predictive model with an 80:20 ratio indicates a realistic finding and was classified as the first rank among others. The AUC value for the training dataset is 0.931, while the AUC value for the testing dataset is 0.964. These attempts will help a great deal when it comes to choosing the best ratio of training samples to testing samples to create a reliable and complete landslide prediction model for the LRB.

Landslide Susceptibility Mapping under the Climate Change Impact in the Chania Regional Unit, West Crete, Greece

Over the preceding decades, climate change has affected precipitation, the most common factor triggering landslides. The aim of this study is to highlight this impact by examining the precipitation trends in the Chania regional unit, Greece, with the help of the precipitation time series provided by 21 local meteorological stations covering a period from 1955 to 2020. The analysis also focuses on the extreme precipitation events of February 2019, where the monthly cumulated precipitation amount reached 1225 mm, one of the highest ever recorded in Greece. Moreover, an inventory of past and recent landslides was created and the intensity–duration landslide precipitation thresholds were evaluated. Daily simulations of precipitation from three state-of-the-art regional climate models were used to analyze precipitation patterns under two representative concentration pathways (RCPs), 4.5 and 8.5, for the period 2030–2060. The application of the estimated precipitation thresholds on the daily future precipitation projections revealed an increase in the following decades of the precipitation events that can activate a landslide and, therefore, highlighted the climate change impact. Moreover, the mean annual precipitation of the preceding 10 years was evaluated and used along with local hydro-geological data and the recent landslide inventory, providing approximately a 5% more effective landslide susceptibility map compared with the relative maps produced by using the mean annual precipitation evaluated for the control period (1976–2005) and for the preceding 30 years. Thus, landslide susceptibility emerges as a dynamic process and the landslide susceptibility map needs to be regularly updated due to the significant and ongoing changes in precipitation because of climate change.

Uncertainties of landslide susceptibility prediction: Influences of different spatial resolutions, machine learning models and proportions of training and testing dataset

This study aims to reveal the impacts of three important uncertainty issues in landslide susceptibility prediction (LSP), namely the spatial resolution, proportion of model training and testing datasets and selection of machine learning models. Taking Yanchang County of China as example, the landslide inventory and 12 important conditioning factors were acquired. The frequency ratios of each conditioning factor were calculated under five spatial resolutions (15, 30, 60, 90 and 120 ​m). Landslide and non-landslide samples obtained under each spatial resolution were further divided into five proportions of training and testing datasets (9:1, 8:2, 7:3, 6:4 and 5:5), and four typical machine learning models were applied for LSP modelling. The results demonstrated that different spatial resolution and training and testing dataset proportions induce basically similar influences on the modeling uncertainty. With a decrease in the spatial resolution from 15 ​m to 120 ​m and a change in the proportions of the training and testing datasets from 9:1 to 5:5, the modelling accuracy gradually decreased, while the mean values of predicted landslide susceptibility indexes increased and their standard deviations decreased. The sensitivities of the three uncertainty issues to LSP modeling were, in order, the spatial resolution, the choice of machine learning model and the proportions of training/testing datasets.

Landslide Susceptibility Spatial Modelling Using Random Forest Algorithm: A Case Study of Malang Regency

Landslides are disasters that cause huge losses to both human life and infrastructure. Therefore, this research purpose of carrying out landslide susceptibility spatial modelling using a random forest (RF) algorithm. This research uses 12 landslide conditioning factors to generate a landslide susceptibility map, which comprises elevation, slope, aspect, soil type, geological type, distance to river, NDVI (Normalized Different Index), river density, TWI (Topographic Wetness Index), annual rainfall, and land use. Each model was evaluated by 9 parameters including ROC (Receiver Operator Characteristic)-AUC (Area Under Curve), accuracy (acc), sensitivity (sn), specificity (sp), balanced accuracy (ba), g-mean (gm), cohen’s kappa (CK), and Matthew’s correlation coefficient (MCC). A total of 88 landslide locations were identified in Malang District using the regional disaster management authority of Malang District data. Of the 88 landslide inventories, 30% of the data were used for validation, and the remaining 70% were used for training purposes. The results show the ACC value of 0.884, 0.765 for SN, 0.962 for SP, 0.863 for GM, 0.857 for BA, 0.749 for CK, 0.876 for MCC, and 0.943 for AUC. From the entire landslide conditioning factors, the elevation parameter has the highest relative contribution level value, which is 100%. Moreover, the susceptibility map indicates that Malang District is dominated by a high susceptibility with an area of 177,208.83 ha (51% of the coverage area). 13 sub-districts that are dominated by high susceptibility levels area, including Ngantang, Kasembon, Apelgading, Pujon, Tirtoyudo, Poncokusumo, Sumbermanjing, Jabung, Dampit, Wonosari, Wagir, Dau and Gedangan sub-districts.

Accuracy Improvement of Different Landslide Susceptibility Evaluation Models through K‐Means Clustering: A Case Study on China’s Funing County

Landslides occur in most countries. As one of the most serious geological hazards, landslides affect infrastructure construction. Thus, it is vital to prepare reliable landslide susceptibility evaluation maps to avoid landslide‐prone areas for various construction projects. In recent years, supervised machine learning algorithms have been widely used in landslide susceptibility evaluation, but many flaws remain in the selection of nonlandslide point samples for comparative analysis. It is significant to improve the authenticity of sample data and reduce the impact of noise. China’s Funing County was used as a case study in this paper, which first identified 122 landslide incidents based on historical data, fieldwork, and remote sensing images to create a landslide inventory in the research area. In addition, 12 causal factors of landslides were determined, including elevation, slope, aspect, plan curvature, profile curvature, distance to roads, distance to rivers, distance to faults, rainfall, normalized difference vegetation index (NDVI), lithology, and land cover. K‐means clustering was used to purify the factor data factors before data‐driven certainty factor (CF) and frequency ratio (FR) models, and machine learning models, random forest (RF) and artificial neural network (ANN), were used for a comparative study on landslide susceptibility evaluation in Funing County. The results show that the selection method of nonlandslide sample data will affect the accuracy of different evaluation models. The purified sample data improved the prediction accuracy of the four models, with significant prediction accuracy improvements observed in the ANN model. The purification of nonlandslide sample data by K‐means method is of great significance for the drawing of landslide sensitivity map.

Inventory and Spatial Distribution of Ancient Landslides in Hualong County, China

The establishment of a regional historical landslide inventory plays an indispensable role in landslide assessment and prevention. In this study, based on the Google Earth platform, an inventory of ancient landslides in Hualong County, Qinghai Province was established. The inventory includes 3517 ancient landslides with individual areas ranging from 2354.6 m2 to 12.44 km2. The dominant characteristics include an elevation of 2600–2800 m, slope of 10–20°, aspects SW, W, and NW, mudstone and sandstone of Paleoproterozoic, Neoproterozoic and Quaternary loess, 8–10 km from faults, 0–1 km from rivers, cultivated and grassland types, NDVI of 0.25–0.3, and an average precipitation in the range of 480–500 mm. In addition, the geometric analysis of landslides shows that the average height and length of ancient landslides in the study area are 151.92 m and 429.52 m, respectively. The power law relationship between the two is L = 0.41 × H1.37. The ancient landslide inventory of this study exhibits an integrated pattern of the development characteristics and spatial distribution of landslides in the Tibetan Plateau and the upper Yellow River basin, as well as providing a significant reference for subsequent landslide susceptibility mapping in the area.

Distribution and Dynamic Behaviors of Landslide in Rangun Khola Watershed of the Western Nepal

Being a major devastating hazard, the study of landslides in Nepal Himalaya is very essential. For controlling and mitigate measures, understanding the behaviors and distribution of landslides over the temporal and spatial range is indispensable. The current study is carried out in the Rangun Khola watershed of western Nepal which spreads from Mahabharat Range (2,500m) to Dun valley covering an area of 489.39 km2. Polygon-based landslide inventory within the temporal range of 18 years (2003 to 2020 AD) was prepared by using temporal series of Google Earth Pro, Sentinel-2 images, and Landsat images, which were verified during the field visit. The number of landslides and area covered in different spatial units and temporal intervals were analyzed using the Q-GIS. In total, 494 landslides were identified and the area covered by the landslide was 0.47% of the total study area. Landslides in this area are highly dynamic with different activity states and temporal fluctuation. The number of landslides were highest, i.e., 143, in 2005 and the Upper Siwalik region consist of a large number of landslides making them highly prone to landslide events. The presence of thrust and faults was also found to be influencing the landslides and size distribution. The study will be useful for further researches to map susceptibility and hazard and also for policymakers to understand landslide status to reduce the risk.

Application of statistical and machine learning techniques for landslide susceptibility mapping in the Himalayan road corridors

Abstract Landslides are frequent geological hazards, mainly in the rainy season along road corridors worldwide. In the present study, we have comparatively analyzed landslide susceptibility by employing integrated geospatial approaches, i.e., data-driven, knowledge-driven, and machine learning (ML), along the main road corridors of the Muzaffarabad district. The landslide inventory of three road corridors is developed to evaluate landslide susceptibility, and eleven landslide causative factors (LCFs) were analyzed. After statistical significance analysis, these eleven LCFs generated susceptibility models using WoE, AHP, LR, and RF. Distance from roads, landcover, lithological units, and slopes are considered more influential LCFs. The performance matrix of different LSMs is evaluated through the area under the curve (AUC-ROC), overall accuracy, Kappa index, F1 score, Mean Absolute Error, and Root Mean Square Error. The AUC-ROC for WoE, AHP, LR, and RF techniques along Neelum road is 0.86, 0.82, 0.91, and 0.97, respectively, along Jhelum Valley road is 0.83, 0.81, 0.93, and 0.95, respectively, while along Kohala road is 0.89, 0.88, 0.89, and 0.92, respectively. The produced LSMs through ML (i.e., RF and LR) showed better prediction accuracies than WoE and AHP along these three road corridors. The LSMs are categorized into very high, high, moderate, and low susceptible zones along these roads. The LSM generated through hybrid models can facilitate the concerned local agencies to implement landslide mitigation policies for the landslide-prone zones along road corridors.

Landslide Susceptibility Mapping Using Machine Learning Approach: A Case Study of Baglung District, Nepal

Assessment of Landslide Susceptibility Map (LSM) is crucial to the reduction of risk of the landslides. This paper focusses on modelling LSM using two different machine learning algorithms namely Random Forest (RF), and Classification and Regression Tree (CART). Ten landslide causative factors along with an inventory of landslides containing 89 recent and historic landslide points, and 90 randomly generated nonlandslide points were used to prepare a susceptibility map. The study area; Baglung district is located in the Gandaki province of Nepal, a highly landslide susceptible zone. Frequency ratio (FR) of each class of conditioning factors were calculated. FR values of landslide and non-landslide points were extracted from normalized FR classified raster. The extracted FR values of each point (landslide and non-landslide) was randomly split into training (70%) and testing (30%) samples which were used for training and testing the model. The performance of each algorithm was evaluated using receiver operating characteristics (ROC) curves in combination with area under the curve (AUC) and error matrix. The AUC results introduced success rate of 1 and 0.88 for RF and CART respectively. Also, the rates of prediction were 0.86 and 0.96 for RF and CART respectively. Similarly, RF and CART showed accuracy of 0.88 and 0.83 from confusion matrix. Therefore, the RF algorithm was superior to CART in identifying the regions at risk for future landslides in the study area. The outcomes of this study is useful and essential for the government, planners, researchers, decision makers and general landuse planners.

Landslide Susceptibility Prediction: Improving the Quality of Landslide Samples by Isolation Forests

Landslide susceptibility prediction (LSP) is the first step to ease landslide disasters with the application of various machine learning methods. A complete landslide inventory, which is essential but difficult to obtain, should include high-quality landslide and non-landslide samples. The insufficient number of landslide samples and the low purity of non-landslide samples limit the performance of the machine learning models. In response, this study aims to explore the effectiveness of isolated forest (IF) to solve the problem of insufficient landslide samples. IF belongs to unsupervised learning, and only a small share of landslide samples in the study area were required for modeling, while the remaining samples were used for testing. Its performance was compared to another advanced integration model, adaptive boosting integrated with decision tree (Ada-DT), which belongs to two-class classifiers (TCC) and needs a sufficient number of samples. Huangpu District, Guangzhou City, Guangdong Province in China, was selected as the study area, and 13 predisposing factors were prepared for the modeling. Results showed that the IF proved its effectiveness with an AUC value of 0.875, although the Ada-DT model performed better (AUC = 0.921). IF outperformed the Ada-DT model in terms of recognizing landslides, and the sensitivity values of IF and the Ada-DT model were 90.00% and 86.67%, respectively, while the Ada-DT model performed better in terms of specificity. Two susceptibility maps obtained by the models were basically consistent with the field investigation, while the areas predicted by IF tended to be conservative as higher risk areas were presented, and the Ada-DT model was likely to be risky. It is suggested to select non-landslide samples from the very low susceptibility areas predicted by the IF model to form a more reliable sample set for Ada-DT modeling. The conclusion confirms the practicality and advancement of the idea of anomaly detection in LSP and improves the application potential of machine learning algorithms for geohazards.

Preliminary Analysis of Coseismic Landslides Induced by the 1 June 2022 Ms 6.1 Lushan Earthquake, China

At 17:00 (UTC+8) on 1 June 2022, an Ms 6.1 reverse earthquake struck Lushan County, Ya’an City, Sichuan Province. This earthquake event had a focal depth of 10 km and the epicenter was located at 30.37° N and 102.94° E. The purpose of this study is to document a comprehensive coseismic landslide inventory for this event and analyze the distribution pattern and factors controlling the landslides. After careful visual interpretations, this quake event was determined to have in total triggered about 2352 landslides in an area of 3900 km2, including both shallow disrupted landslides and collapses, for which the spatial distribution was statistically related to regional topography, geology, and seismicity. Notably, a vast majority of the landslides were located on the NW plate of the seismogenic fault, and were distributed in the area with a seismic intensity of VII. In addition, coseismic landslides were more likely to appear in areas with high altitude, relief, and large slope. The landslide area density (LAD) increased with an increase in the above factors and is explained by an exponential relationship, indicating that the occurrence of coseismic landslides in this area was more easily affected by topographic factors than seismic factors. Most small-scale landslides were clustered in the ridge area, which shows the seismic amplification effects of mountain slopes. Due to the impact of seismic wave propagation direction, hillslopes facing northeast-east (NE-E) were more prone to collapse than southwest-facing ones. Based on the distribution pattern of the landslides, we suggest that the seismogenic fault of this event was NW dipping. These findings indicate that it is effective to identify the dipping of seismogenic faults using the spatial distribution pattern of coseismic landslides.