Search

In this paper, we developed highly accurate ensemble machine learning models integrating Reduced Error Pruning Tree (REPT) as a base classifier with the Bagging (B), Decorate (D), and Random Subspace (RSS) ensemble learning techniques for spatial prediction of rainfall-induced landslides in the Uttarkashi district, located in the Himalayan range, India. To do so, a total of 103 historical landslide events were linked to twelve conditioning factors for generating training and validation datasets. Root Mean Square Error (RMSE) and Area Under the receiver operating characteristic Curve (AUC) were used to evaluate the training and validation performances of the models. The results showed that the single REPT model and its derived ensembles provided a satisfactory accuracy for the prediction of landslides. The D-REPT model with RMSE = 0.351 and AUC = 0.907 was identified as the most accurate model, followed by RSS-REPT (RMSE = 0.353 and AUC = 0.898), B-REPT (RMSE = 0.396 and AUC = 0.876), and the single REPT model (RMSE = 0.398 and AUC = 0.836), respectively. The prominent ensemble models proposed and verified in this study provide engineers and modelers with insights for development of more advanced predictive models for different landslide-susceptible areas around the world. [ABSTRACT FROM AUTHOR]

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

The Himalayan region with its complex geological features, steep slopes, rugged topography, and intense monsoonal rainfall create ideal conditions for landslides. The damage caused due to landslides is immense causing significant loss of life and property initiating a dire need to formulate strategies in minimizing its impact in areas affected by landslides. Several attempts have been presented by various researchers in order to establish rainfall intensity thresholds using various parameters of rainfall conditions. These methods provide deterministic thresholds, i.e., landslide or no landslide; such thresholds are not always suited for landslides. In this paper, rainfall thresholds have been evaluated using a statistical method which results in the probability of landslide occurrence for single or multiple rainfall parameters leading to slide initiation. The results are expressed in terms of probabilities by analyzing two different variants of Bayes theorem, i.e., 1D and 2D. Probabilistic thresholds were calculated for Kalimpong region of Darjeeling Himalayas using available rainfall and landslide data during the year 2010-2016. The probabilities calculated for landslide occurrence were found to be 0.37 for rainfall intensity greater than 10 mm/day. However, the probability for a combination of rainfall intensity of 30 mm/day with duration of 3 days was calculated to be 0.67. The results also depicted that landslides are related to rainfall event parameters especially with rainfall intensity. [ABSTRACT FROM AUTHOR]

Slope units represent surface slopes by means of polygons delimited by drainage and divide lines obtained on a digital topography. Objective slope unit delineation for a given digital elevation model is still an open issue and, often, a limitation that may dictate the use of a more traditional pixel-based approach for spatial analysis. Availability of slope unit maps facilitates many kinds of studies and allows scholars to focus on specific scientific issues rather than on preparing sound mapping units from scratch for their research. Here, we present a slope unit map of a large portion of the Himalayas. The map is prepared following a widely tested, parameter-free optimization algorithm. The area encompassed by the map is relevant to studies of the well-known 2015 Gorkha earthquake and monsoons, which makes it relevant to a vast portion of the scientific community working in natural hazards including, but not limited to, landslide scientists and practitioners. The map contains 112,674 polygons with average area of 0.38 km² and is published in vector form. The map is accompanied by a selection of data including morphometric and thematic quantities. In addition to describing the rationale behind the delineation of the polygonal map and selected data, we describe an application devoted to unsupervised terrain classification. We applied a k-means clustering procedure with two strategies: one at (coarser) basin scale and one at (finer) slope unit scale. We show similarities and differences between the two classification strategies, highlighting the role of the slope unit subdivision in the two cases. [ABSTRACT FROM AUTHOR]

An attempt is made to explain the relationship of landslides to litho-tectonic and precipitation regimes. The possible influence of these factors on the dimensional pattern of landslides is also inferred. The Yamuna River valley, NW Himalaya, which traverses the Higher Himalaya (HH) and Lesser Himalaya (LH) rock mass, endures disastrous landslides and hence is taken as the case for study. To achieve the objectives, proxies like stream length gradient, topographic profile, steepness index, and ratio of valley floor width to valley height were used to infer a spatially varying tectonic regime, whereas rainfall data and Normalized Difference Vegetation Index were used to determine spatial differences in precipitation and vegetation variability, respectively. Dimensional patterns of landslides utilized the landslide area and volume. The higher reaches of the HH and lowest part of the LH show rockfall dominance associated with relatively high tectonic activity, whereas most of the debris slides coincide with regional thrusts. Total area and volume occupied by the landslides are ~1.5 ± 0.16 × 106 m2 and ~4.7 ± 1.2 × 106 m3, respectively. Dimensions of debris slides were found to be less influenced by the litho-tectonic and precipitation regimes, whereas the dimensions of rockfalls were found to be more sensitive to these conditions. [ABSTRACT FROM AUTHOR]

This study uses a deterministic approach to evaluate the factor of safety (FS) of the terrain for different hydrological conditions, in part of Indian Lesser Himalaya. The results indicate sudden increase in the percentage unstable area from 7.5% to 13.8% for rainfall intensity variation from 50 to 100 mm/day. For the rainfall intensity of 15 August 2007 which caused many landslides in the study area, 18.5% of the total area was unstable and it increases to 21.7%, 23.5% and 24.7%, respectively, for rainfall intensities corresponding to 10, 25 and 50 year return periods. This increment stagnates at about 260 mm/day, making about 25% of the area unstable. Higher rainfall intensities make progressively gentler slopes unstable, but limited to 25 degrees of slope in this area. The area underlain by granitic gneiss showed 23.1% of area as unstable for 135 mm/day of rainfall intensity, and was followed by those areas underlain by amphibolite (16%), limestone (13.7%) and quartzite (10.4%). Receiver operating characteristic (ROC) curve analysis has given 84.2% accuracy for the model. Conversion of FS to failure probability throughZscores enables identification unstable or marginally unstable areas, for planning selective slope stabilization measures. [ABSTRACT FROM AUTHOR]

Landslides cause widespread damage in the Himalayas. Landslide Hazard Zonation is important to take quick and safe mitigation measures and make strategic planning for the future. A part of the Bhagirathi Valley in the Garhwal Himalaya was selected for landslide hazard zonation. The study utilized different types of data including Survey of India topographic maps, geological (lithological and structural) maps, IRS-1B and-1D multispectral and PAN satellite sensor data and field observations. The processing of multi-geodatasets was carried out in a raster GIS environment. The various data layers generated and co-registered were: landuse/landcover, buffer map of thrusts, buffer map of photo-lineaments, lithology, buffer map of drainage, slope angle and relative relief. Data integration was carried out using the ordinal scale (qualitative) relative weighting rating technique to give a Landslide Hazard Index (LHI) value. The breaks in the LHI frequency diagram were used to delineate various landslide hazard zones, namely, very low, low, moderate, high and very high. Field data on landslides were employed to evaluate and validate landslide hazard zonation map. It is interpreted that the distribution of landslides is largely governed by a combination of geoenvironmental conditions like proximity (>500 m) to the thrust zone, presence of Munsiari Formation (Higher Himalayan Crystalline) and barren or less-vegetated areas. [ABSTRACT FROM AUTHOR]