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.     

A Novel Classifier Based on Composite Hyper-cubes on Iterated Random Projections for Assessment of Landslide Susceptibility

In this paper, the main objective is to discover an application of a novel classifier based on Composite Hyper-cubes on Iterated Random Projections (CHIRP) for assessment of landslide susceptibility at the Uttarakhand Area (India). For this, 1295 historical landslides events and landslide affecting parameters were collected and used for creating training and testing datasets. Other benchmark models namely Logistic Regression (LR), RBF neural network (ANN-RBF), and Naïve Bayes (NB) were chosen for comparison. Analysis results indicate that the CHIRP is the best, followed by the LR, the ANN-RBF, and the NB, respectively. Overall, the CHIRP indicates as a promising and good alternative method that could be used to assess landslide susceptibility in other landslide prone areas.     

Investigation of ground rotational motions caused by direct and scattered P-waves from the 4 March 2008 TAIGER explosion experiment

High-frequency rotational motions of P-waves and coda waves were analysed using rotation rate sensors and strong motion array data from the 4 March 2008 TAiwan Integrated GEodynamics Research (TAIGER) explosion experiment in northeastern Taiwan. Theoretical and observational investigations focussed on the effects of this experiment on the free surface. The main goal of this study was to explore possible applications of combined measurements of artificial explosion-derived translational and rotational motions. Also investigated was the consistent ground rotation observed directly by rotation rate sensors and derived using translational seismic arrays. Common near-source high-frequency rotational motion observations and array-recorded translational motions from one shallow borehole explosion are analysed in this study. Using a half-space assumption of plane P-wave propagation across the recording site, we conclude that: (1) rotational motions induced by direct P-waves interacting with a free surface in theory can be used to estimate wave radial direction, velocity and anisotropic properties; (2) rotational motions derived from scattering are predominant among the observed rotations during the TAIGER explosion experiments and allow us to image the heterogeneous structure of the medium at the investigated site; and (3) rotation sensor measurements undertaken during TAIGER explosion experiments may be affected by cross-axis sensitivities, which need to be considered when using the data obtained during these experiments.     

Damage detection of a thin plate using modal curvature via macrostrain measurement

Plate structures are employed as important structural components in many engineering applications. Hence, assessing the structural conditions of in-service plate structures is critical to monitoring global structural health. Modal curvature-based damage detection techniques have recently garnered considerable attention from the research community, and have become a promising vibration-based structural health monitoring solution. However, computing errors arise when calculating modal curvatures from lateral mode shapes, which result from unavoidable measurement errors in the mode shapes as identified from lateral vibration signals; this makes curvature-based algorithms that use a lateral measurement only theoretically feasible, but practically infeasible. Therefore, in this study, long-gauge fiber Bragg grating strain sensors are employed to obtain a modal curvature without a numerical differentiation procedure in order to circumvent the computing errors. Several damage indices based on modal curvatures that were developed to locate beam damage are employed. Both numerical and experimental studies are performed to validate the proposed approach. However, although previous studies have reported relative success with the application of these damage indices on a simple beam, only one damage index demonstrated the capability to locate damage when the stiffness of the local region changed near the sensor.     

Bayesian Chance‐Constrained Hydraulic Barrier Design under Geological Structure Uncertainty

The groundwater community has widely recognized geological structure uncertainty as a major source of model structure uncertainty. Previous studies in aquifer remediation design, however, rarely discuss the impact of geological structure uncertainty. This study combines chance‐constrained (CC) programming with Bayesian model averaging (BMA) as a BMA‐CC framework to assess the impact of geological structure uncertainty in remediation design. To pursue this goal, the BMA‐CC method is compared with traditional CC programming that only considers model parameter uncertainty. The BMA‐CC method is employed to design a hydraulic barrier to protect public supply wells of the Government St. pump station from salt water intrusion in the “1500‐foot” sand and the “1700‐foot” sand of the Baton Rouge area, southeastern Louisiana. To address geological structure uncertainty, three groundwater models based on three different hydrostratigraphic architectures are developed. The results show that using traditional CC programming overestimates design reliability. The results also show that at least five additional connector wells are needed to achieve more than 90% design reliability level. The total amount of injected water from the connector wells is higher than the total pumpage of the protected public supply wells. While reducing the injection rate can be achieved by reducing the reliability level, the study finds that the hydraulic barrier design to protect the Government St. pump station may not be economically attractive.     

A hybrid machine learning ensemble approach based on a Radial Basis Function neural network and Rotation Forest for landslide susceptibility modeling: A case study in the Himalayan area,India

In this paper, a hybrid machine learning ensemble approach namely the Rotation Forest based Radial Basis Function (RFRBF) neural network is proposed for spatial prediction of landslides in part of the Himalayan area (India). The proposed approach is an integration of the Radial Basis Function (RBF) neural network classifier and Rotation Forest ensemble, which are state-of-the art machine learning algorithms for classification problems. For this purpose, a spatial database of the study area was established that consists of 930 landslide locations and fifteen influencing parameters (slope angle, road density, curvature, land use, distance to road, plan curvature, lineament density, distance to lineaments, rainfall, distance to river, profile curvature, elevation, slope aspect, river density, and soil type). Using the database, training and validation datasets were generated for constructing and validating the model. Performance of the model was assessed using the Receiver Operating Characteristic (ROC) curve, area under the ROC curve (AUC), statistical analysis methods, and the Chi square test. In addition, Logistic Regression (LR), Multi-layer Perceptron Neural Networks (MLP Neural Nets), Naïve Bayes (NB), and the hybrid model of Rotation Forest and Decision Trees (RFDT) were selected for comparison. The results show that the proposed RFRBF model has the highest prediction capability in comparison to the other models (LR, MLP Neural Nets, NB, and RFDT); therefore, the proposed RFRBF model is promising and should be used as an alternative technique for landslide susceptibility modeling.     

豫西地区秦岭造山带武当群火山岩和沉积岩锆石U-Pb年龄

在南秦岭地体中广泛分布着武当群变质沉积-火山岩组合的基底岩石,是东秦岭造山带重要的岩石单元,但对其形成时代的认识存在分歧.笔者通过对豫西地区武当地体北部武当群上部杨坪组变质沉积岩和下部双台组变质中酸性火山岩锆石u-Pb年龄的测定,认为杨坪组变质沉积岩沉积物源主要由晚元古代(860～640 Ma)和早元古代(2260～1800 Ma)、少量晚太古代和中元古代地壳物质构成,与扬子陆块具有亲缘关系.沉积时代应晚于640 Ma.变质中酸性火山岩形成时代为730～780 Ma之间,峰值(755±6)Ma,与双台组新元古代变质基性火山岩为同期岩浆作用的产物,成因上推测与Rodinia超大陆裂解作用有关.     

A Novel Intelligent ELM-BBO Technique for Predicting Distance of Mine Blasting-Induced Flyrock

Natural Resources Research - Blasting is an economical technique for rock breaking in hard rock excavation. One of its complex undesired environmental effects is flyrock, which may result in human...     

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...     

重力方法研究越南早新生代基底效果分析(英文)

为了提高用重力方法在越南研究早新生代基底结构特点中的效率,表明作者们提出了一个综合分析地质及地球物理资料的系统方法.获得的研究结果表明:1)一个大的平均密度差是在用重力方法研究越南的早新生代基底时效率的一个基本因素;2)用多维线性相关分析来有效研究和预测越南的早新生代基底岩石的埋藏深度与密度是有可能的;3)通过利用多维线性分析预测密度以及泊松系数使我们能预测早新生代基底岩石.