Landslide Hazard Assessment Using Random SubSpace Fuzzy Rules Based Classifier Ensemble and Probability Analysis of Rainfall Data: A Case Study at Mu Cang Chai District,Yen Bai Province (Viet Nam)

Landslide hazard assessment at the Mu Cang Chai district; Yen Bai province (Viet Nam) has been done using Random SubSpace fuzzy rules based Classifier Ensemble (RSSCE) method and probability analysis of rainfall data. RSSCE which is a novel classifier ensemble method has been applied to predict spatially landslide occurrences in the area. Prediction of temporally landslide occurrences in the present study has been done using rainfall data for the period 2008–2013. A total of fifteen landslide influencing factors namely slope, aspect, curvature, plan curvature, profile curvature, elevation, land use, lithology, rainfall, distance to faults, fault density, distance to roads, road density, distance to rivers, and river density have been utilized. The result of the analysis shows that RSSCE and probability analysis of rainfall data are promising methods for landslide hazard assessment. Finally, landslide hazard map has been generated by integrating spatial prediction and temporal probability analysis of landslides for the land use planning and landslide hazard management.     

Mechanism of two rapid and long-runout landslides in the 16 April 2016 Kumamoto earthquake using a ring-shear apparatus and computer simulation (LS-RAPID)

Around hundred landslides were triggered by the Kumamoto earthquakes in April 2016, causing fatalities and serious damage to properties in Minamiaso village, Kumamoto Prefecture, Japan. The landslides included many rapid and long-runout landslides which were responsible for much of the damage. To understand the mechanism of these earthquake-triggered landslides, we carried out field investigations with an unmanned aerial vehicle to obtain DSM and took samples from two major landslides (Takanodai landslide and Aso-ohashi landslide) to measure parameters of the initiation and the motion of landslides. A series of ring-shear tests and computer simulations were conducted using a measured Kumamoto earthquake acceleration record from KNet station KMM005, 10 km west of Aso-ohashi landslide. The research results supported our assumed mechanism of sliding-surface liquefaction for the rapid and long-runout motion of these landslides.     

Prediction of Blast-Induced Ground Vibration in Open-Pit Mines Using a New Technique Based on Imperialist Competitive Algorithm and M5Rules

Natural Resources Research - In this paper, blast-induced ground vibration (BIGV) was considered as the primary objective, and a new artificial intelligence system was proposed to predict BIGV with...     

The October 13, 2020, deadly rapid landslide triggered by heavy rainfall in Phong Dien,Thua Thien Hue,Vietnam

Landslides - At about 12:00 a.m., on October 13, 2020, a rapid rotational landslide induced by rainfall swept over Ranger Station-7 in Phong Xuan commune, Phong Dien district, Thua Thien Hue...     

Marble-hosted ruby deposits from Central and Southeast Asia: Towards a new genetic model

Marble-hosted ruby deposits represent the most important source of colored gemstones from Central and South East Asia. These deposits are located in the Himalayan mountain belt which developed during Tertiary collision of the Indian plate northward into the Eurasian plate. They are spatially related to granitoid intrusions and are contained in platform carbonates series that underwent high-grade metamorphism. All occurrences are located close to major tectonic features formed during Himalayan orogenesis, directly in suture zones in the Himalayas, or in shear zones that guided extrusion of the Indochina block after the collision in South East Asia. Ar–Ar dating of micas syngenetic with ruby and U–Pb dating of zircon included in ruby gives evidence that these deposits formed during Himalayan orogenesis, and the ages document the extensional tectonics that were active, from Afghanistan to Vietnam, between the Oligocene and the Pliocene.The petrography shows that ruby-bearing marbles formed in the amphibolite facies (T = 610 to 790 °C and P ~ 6 kbar). A fluid inclusion study defines the conditions of gem ruby formation during the retrograde metamorphic path (620 < T < 670 °C and 2.6 < P < 3.3 kbar) for the deposits of Jegdalek, Hunza and northern Vietnam.Whole rock analyses of non-ruby-bearing marbles indicate that they contain enough aluminum and chromiferous elements to produce all the ruby crystals that they contain. In addition, (C, O)-isotopic analyses of carbonates from the marbles lead to the conclusion that the marbles acted as a metamorphic closed fluid system that were not infiltrated by externally-derived fluids. The carbon isotopic composition of graphite in marbles reveals that it is of organic origin and that it exchanged C-isotopes with the carbonates during metamorphism. Moreover, the O-isotopic composition of ruby was buffered by metamorphic CO₂ released during devolatilisation of marble and the H-isotopic composition of mica is consistent with a metamorphic origin for water in equilibrium with the micas. The (C, O, H)-isotopic compositions of minerals associated with marble-hosted ruby are all in agreement with the hypothesis, drawn from the unusual chemistry of CO₂–H₂S–COS–S₈–AlO(OH)-bearing fluids contained in fluid inclusions, that gem ruby formed at P ~ 3 kbar and 620 < T < 670 °C, during thermal reduction of evaporite by organic matter, at high temperature-medium pressure metamorphism of platform carbonates during the Tertiary India–Asia collision. The carbonates were enriched in Al- and chromiferous-bearing detrital minerals, such as clay minerals that were deposited on the platform with the carbonates, and in organic matter. Ruby formed during the retrograde metamorphic path, mainly by destabilization of muscovite or spinel. The metamorphic fluid system was rich in CO₂ released from devolatilisation of carbonates, and in fluorine, chlorine and boron released by molten salts (NaCl, KCl, CaSO₄). Evaporites are key to explaining the formation of these deposits. Molten salts mobilized in situ Al and metal transition elements contained in marbles, leading to crystallization of ruby.     

Spatial prediction of landslide susceptibility in western Serbia using hybrid support vector regression (SVR) with GWO,BAT and COA algorithms

In this study, we developed multiple hybrid machine-learning models to address parameter optimization limitations and enhance the spatial prediction of landslide susceptibility models. We created a geographic information system database, and our analysis results were used to prepare a landslide inventory map containing 359 landslide events identified from Google Earth, aerial photographs, and other validated sources. A support vector regression (SVR) machine-learning model was used to divide the landslide inventory into training (70%) and testing (30%) datasets. The landslide susceptibility map was produced using 14 causative factors. We applied the established gray wolf optimization (GWO) algorithm, bat algorithm (BA), and cuckoo optimization algorithm (COA) to fine-tune the parameters of the SVR model to improve its predictive accuracy. The resultant hybrid models, SVR-GWO, SVR-BA, and SVR-COA, were validated in terms of the area under curve (AUC) and root mean square error (RMSE). The AUC values for the SVR-GWO (0.733), SVR-BA (0.724), and SVR-COA (0.738) models indicate their good prediction rates for landslide susceptibility modeling. SVR-COA had the greatest accuracy, with an RMSE of 0.21687, and SVR-BA had the least accuracy, with an RMSE of 0.23046. The three optimized hybrid models outperformed the SVR model (AUC = 0.704, RMSE = 0.26689), confirming the ability of metaheuristic algorithms to improve model performance.     

Stochastic Modeling of Groundwater Fluoride Contamination: Introducing Lazy Learners

While it remains the primary source of safe drinking and irrigation water in northwest Iran's Maku Plain, the region's groundwater is prone to fluoride contamination. Accordingly, modeling techniques to accurately predict groundwater fluoride concentration are required. The current paper advances several novel data mining algorithms including Lazy learners [instance-based K-nearest neighbors (IBK); locally weighted learning (LWL); and KStar], a tree-based algorithm (M5P), and a meta classifier algorithm [regression by discretization (RBD)] to predict groundwater fluoride concentration. Drawing on several groundwater quality variables (e.g., concentrations), measured in each of 143 samples collected between 2004 and 2008, several models predicting groundwater fluoride concentrations were developed. The full dataset was divided into two subsets: 70% for model training (calibration) and 30% for model evaluation (validation). Models were validated using several statistical evaluation criteria and three visual evaluation approaches (i.e., scatter plots, Taylor and Violin diagrams). Although Na⁺ and Ca²⁺ showed the greatest positive and negative correlations with fluoride (r = 0.59 and −0.39, respectively), they were insufficient to reliably predict fluoride levels; therefore, other water quality variables, including those weakly correlated with fluoride, should be considered as inputs for fluoride prediction. The IBK model outperformed other models in fluoride contamination prediction, followed by KStar, RBD, M5P, and LWL. The RBD and M5P models were the least accurate in terms of predicting peaks in fluoride concentration values. Results of the current study can be used to support practical and sustainable management of water and groundwater resources.     

A Comparative Study of Least Square Support Vector Machines and Multiclass Alternating Decision Trees for Spatial Prediction of Rainfall-Induced Landslides in a Tropical Cyclones Area

The objective of this study is to explore and compare the least square support vector machine (LSSVM) and multiclass alternating decision tree (MADT) techniques for the spatial prediction of landslides. The Luc Yen district in Yen Bai province (Vietnam) has been selected as a case study. LSSVM and MADT are effective machine learning techniques of classification applied in other fields but not in the field of landslide hazard assessment. For this, Landslide inventory map was first constructed with 95 landslide locations identified from aerial photos and verified from field investigations. These landslide locations were then divided randomly into two parts for training (70 % locations) and validation (30 % locations) processes. Secondly, landslide affecting factors such as slope, aspect, elevation, curvature, lithology, land use, distance to roads, distance to faults, distance to rivers, and rainfall were selected and applied for landslide susceptibility assessment. Subsequently, the LSSVM and MADT models were built to assess the landslide susceptibility in the study area using training dataset. Finally, receiver operating characteristic curve and statistical index-based evaluations techniques were employed to validate the predictive capability of these models. As a result, both the LSSVM and MADT models have high performance for spatial prediction of landslides in the study area. Out of these, the MADT model (AUC = 0.853) outperforms the LSSVM model (AUC = 0.803). From the landslide study of Luc Yen district in Yen Bai province (Vietnam), it can be conclude that the LSSVM and MADT models can be applied in other areas of world also for and spatial prediction. Landslide susceptibility maps obtained from this study may be helpful in planning, decision making for natural hazard management of the areas susceptible to landslide hazards.