Evaluation of generalized linear models for soil liquefaction probability prediction

A soil deposit subjected to seismic loading can be viewed as a binary system: it will either liquefy or not liquefy. Generalized linear models are versatile tools for predicting the response of a binary system and hence potentially applicable to liquefaction prediction. In this study, the applicability of four generalized linear models (i.e., logistic, probit, log–log, and c-log–log) for liquefaction potential evaluation is assessed and compared. Eight liquefaction models based on the four generalized linear models and two sets of explanatory variables are evaluated. These models are first calibrated with past liquefaction performance data. A weighted-likelihood function method is used to consider the sampling bias in the calibration database. The predicted liquefaction probabilities from various models are then compared. When liquefaction probability is small, the predicted liquefaction probability is sensitive to the regression models used. The effect of sampling bias is more marked in the high cyclic stress ratio region. The eight models are finally ranked using a Bayesian model comparison method. For the generalized linear models examined, the logistic and c-log–log regression models are most supported by the past performance data. On the other hand, the probit and c-log–log regression models are much less applicable to liquefaction prediction.     

Support vector machines and feed-forward neural networks for spatial modeling of groundwater qualitative parameters

The present study attempts to model the spatial variability of three groundwater qualitative parameters in Guilan Province, northern Iran, using artificial neural networks (ANNs) and support vector machines (SVMs). Data collected from 140 observation wells for the years 2002–2014 were used. Five variables, X and Y coordinates of the observation well, distance of the observation well from the shoreline, areal average 6-month rainfall depth, and groundwater level at the day of water quality sampling, were considered as primary input variables. In addition, nine qualitative variables were also considered as auxiliary input variables. Electrical conductivity (EC), sodium concentration (Na⁺), and sulfate concentration (SO₄ ^2?) of the groundwater in the region were estimated using ANNs and SVMs with different input combinations. The results showed that both ANNs and SVMs work well when the only primary input variable is the well location. The ANN yielded an RMSE of 1.03 mEq/l for SO₄ ^2?, 1.05 mEq/l for Na⁺, and 203.17 μS/cm for EC, using the X and Y coordinates of the observation wells in the study area. In the case of SVM, these values were, respectively, 0.87, 0.87, and 176.68. Considering the auxiliary input variables (pH, EC, and the concentrations of Na⁺, K⁺, Ca²⁺, Mg²⁺, Cl^?, SO₄ ^2?, and HCO₃ ^?) resulted in a significant decrease in the RMSE of both ANNs (0.22, 0.30, and 33.04) and SVMs (0.26, 0.34, and 36.23). Comparing these RMSE values with those of cokriging interpolation technique (0.59, 0.98, and 177.59) indicated that ANNs and SVMs produced more accurate estimates of the three qualitative parameters. The relative importance of auxiliary input variables was also determined using Gamma test. The output uncertainty of ANNs and SVMs were determined using p-factor and d-factor. The results showed that SVMs have less uncertainty than ANNs.     

Machine learning predictive models for mineral prospectivity: An evaluation of neural networks,random forest,regression trees and support vector machines

Machine learning algorithms (MLAs) such us artificial neural networks (ANNs), regression trees (RTs), random forest (RF) and support vector machines (SVMs) are powerful data driven methods that are relatively less widely used in the mapping of mineral prospectivity, and thus have not been comparatively evaluated together thoroughly in this field.The performances of a series of MLAs, namely, artificial neural networks (ANNs), regression trees (RTs), random forest (RF) and support vector machines (SVMs) in mineral prospectivity modelling are compared based on the following criteria: i) the accuracy in the delineation of prospective areas; ii) the sensitivity to the estimation of hyper-parameters; iii) the sensitivity to the size of training data; and iv) the interpretability of model parameters. The results of applying the above algorithms to epithermal Au prospectivity mapping of the Rodalquilar district, Spain, indicate that the RF outperformed the other MLA algorithms (ANNs, RTs and SVMs). The RF algorithm showed higher stability and robustness with varying training parameters and better success rates and ROC analysis results. On the other hand, all MLA algorithms can be used when ore deposit evidences are scarce. Moreover the model parameters of RF and RT can be interpreted to gain insights into the geological controls of mineralization.     

Assessment and calibration of two models for estimation of soil nail loads and system reliability analysis of soil nails against internal failures

Acta Geotechnica - This study first presents accuracy assessments of two default models proposed in two popular soil nail wall design specifications and their calibrated versions for estimation of...     

Spatial prediction models for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines,artificial neural networks,kernel logistic regression,and logistic model tree

Preparation of landslide susceptibility maps is considered as the first important step in landslide risk assessments, but these maps are accepted as an end product that can be used for land use planning. The main objective of this study is to explore some new state-of-the-art sophisticated machine learning techniques and introduce a framework for training and validation of shallow landslide susceptibility models by using the latest statistical methods. The Son La hydropower basin (Vietnam) was selected as a case study. First, a landslide inventory map was constructed using the historical landslide locations from two national projects in Vietnam. A total of 12 landslide conditioning factors were then constructed from various data sources. Landslide locations were randomly split into a ratio of 70:30 for training and validating the models. To choose the best subset of conditioning factors, predictive ability of the factors were assessed using the Information Gain Ratio with 10-fold cross-validation technique. Factors with null predictive ability were removed to optimize the models. Subsequently, five landslide models were built using support vector machines (SVM), multi-layer perceptron neural networks (MLP Neural Nets), radial basis function neural networks (RBF Neural Nets), kernel logistic regression (KLR), and logistic model trees (LMT). The resulting models were validated and compared using the receive operating characteristic (ROC), Kappa index, and several statistical evaluation measures. Additionally, Friedman and Wilcoxon signed-rank tests were applied to confirm significant statistical differences among the five machine learning models employed in this study. Overall, the MLP Neural Nets model has the highest prediction capability (90.2 %), followed by the SVM model (88.7 %) and the KLR model (87.9 %), the RBF Neural Nets model (87.1 %), and the LMT model (86.1 %). Results revealed that both the KLR and the LMT models showed promising methods for shallow landslide susceptibility mapping. The result from this study demonstrates the benefit of selecting the optimal machine learning techniques with proper conditioning selection method in shallow landslide susceptibility mapping.     

Assessment of rainfall thresholds and soil moisture modeling for operational hydrogeological risk prevention in the Umbria region (central Italy)

Rainfall thresholds represent the main tool for the Italian Civil Protection System for early warning of the threat of landslides. However, it is well-known that soil moisture conditions at the onset of a storm event also play a critical role in triggering slope failures, especially in the case of shallow landslides. This study attempts to define soil moisture (estimated by using a soil water balance model) and rainfall thresholds that can be employed for hydrogeological risk prevention by the Civil Protection Decentrate Functional Centre (CFD) located in the Umbria Region (central Italy). Two different analyses were carried out by determining rainfall and soil moisture conditions prior to widespread landslide events that occurred in the Umbria Region and that are reported in the AVI (Italian Vulnerable Areas) inventory for the period 1991?C2001. Specifically, a ??local?? analysis that considered the major landslide events of the AVI inventory and an ??areal?? analysis subdividing the Umbria Region in ten sub-areas were carried out. Comparison with rainfall thresholds used by the Umbria Region CFD was also carried out to evaluate the reliability of the current procedures employed for landslide warning. The main result of the analysis is the quantification of the decreasing linear trend between the maximum cumulated rainfall values over 24, 36 and 48?h and the soil moisture conditions prior to landslide events. This trend provides a guideline to dynamically adjust the operational rainfall thresholds used for warning. Moreover, the areal analysis, which was aimed to test the operational use of the combined soil moisture?Crainfall thresholds showed, particularly for low values of rainfall, the key role of soil moisture conditions for the triggering of landslides. On the basis of these results, the Umbria Region CFD is implementing a procedure aimed to the near real-time estimation of soil moisture conditions based on the soil water balance model developed ad hoc for the region. In fact, it was evident that a better assessment of the initial soil moisture conditions would support and improve the hydrogeological risk assessment.     

Tephra layers from Holocene lake sediments of the Sulmona Basin, central Italy: implications for volcanic activity in Peninsular Italy and tephrostratigraphy in the central Mediterranean area

We present a new tephrostratigraphic record from the Holocene lake sediments of the Sulmona basin, central Italy. The Holocene succession is represented by whitish calcareous mud that is divided into two units, SUL2 (ca 32 m thick) and SUL1 (ca 8 m thick), for a total thickness of ca 40 m. These units correspond to the youngest two out of six sedimentary cycles recognised in the Sulmona basin that are related to the lake sedimentation since the Middle Pleistocene. Height concordant U series age determinations and additional chronological data constrain the whole Holocene succession to between ca 8000 and 1000 yrs BP. This includes a sedimentary hiatus that separates the SUL2 and SUL1 units, which is roughly dated between <2800 and ca 2000 yrs BP. A total of 31 and 6 tephra layers were identified within the SUL2 and SUL1 units, respectively. However, only 28 tephra layers yielded fresh micro-pumices or glass shards suitable for chemical analyses using a microprobe wavelength dispersive spectrometer. Chronological and compositional constraints suggest that 27 ash layers probably derive from the Mt. Somma-Vesuvius Holocene volcanic activity, and one to the Ischia Island eruption of the Cannavale tephra (2920 ± 450 cal yrs BP). The 27 ash layers compatible with Mt. Somma-Vesuvius activity are clustered in three different time intervals: from ca 2000 to >1000; from 3600 to 3100; and from 7600 to 4700 yrs BP. The first, youngest cluster, comprises six layers and correlates with the intense explosive activity of Mt. Somma-Vesuvius that occurred after the prominent AD 79 Pompeii eruption, but only the near-Plinian event of AD 472 has been tentatively recognised. The intermediate cluster (3600–3100 yrs BP) starts with tephra that chemically and chronologically matches the products from the “Pomici di Avellino” eruption (ca 3800 ± 200 yrs BP). This is followed by eight further layers, where the glasses exhibit chemical features that are similar in composition to the products from the so-called “Protohistoric” or AP eruptions; however, only the distal equivalents of three AP events (AP3, AP4 and AP6) are tentatively designated. Finally, the early cluster (7600–4700 yrs BP) comprises 12 layers that contain evidence of a surprising, previously unrecognised, activity of the Mt. Somma-Vesuvius volcano during its supposed period of quiescence, between the major Plinian “Pomici di Mercato” (ca 9000 yrs BP) and “Pomici di Avellino” eruptions. Alternatively, since at present there is no evidence of a similar significant activity in the proximal area of this well-known volcano, a hitherto unknown origin of these tephras cannot be role out. The results of the present study provide new data that enrich our previous knowledge of the Holocene tephrostratigraphy and tephrochronology in central Italy, and a new model for the recent explosive activity of the Peninsular Italy volcanoes and the dispersal of the related pyroclastic deposits.     

Surface water and groundwater dynamic interaction models as guiding tools for optimal conjunctive water use policies in the central plain of Thailand

Many irrigation projects in the central plain of Thailand are not capable of providing sufficient surface water for the cultivation of rice, which is the major cash crop for Thai farmers. To overcome this surface water deficiency, which has been exacerbated in recent years by climate change, groundwater is increasingly being used for irrigation. Thus, large sections of agriculture lands have been converted to conjunctive water use regions. While conjunctive water use may be a suitable option to overcome the temporary water shortages on a short-term basis, it may pose a particular threat to the overall water resources in the long term, if not properly managed. As a remedy, conjunctive water management policies ought to be adopted. Conjunctive water management is basically a tool to optimize productivity, equity, and environmental sustainability through simultaneous management of surface water and groundwater resources. As of now, such a comprehensive approach has not been yet employed in the upper Chao Phraya basin of Thailand, and the present study is one of the first of this kind. The study region is the Plaichumpol Irrigation Project (PIP) where conjunctive water use has become indispensable for meeting the increasing water requirements for farming. To get a first grip on the issue, water demand, supply and actual use in the study area were investigated for the purpose of providing possible guidelines for optimal water exploitation. A numerical groundwater model with a special module for simulating surface-groundwater interaction was applied in the PIP area to understand the impact of the farmer’s irrigation behavior on the dominant hydrological processes that determine the seasonal and multi-annual water availability in the irrigation area. A set-up of different agricultural water allocation schemes that depend on the local weather conditions and the regional management rules are examined by the numerical models. The results of the simulations provide adaptation guidelines for the proper management of the conjunctive water resources, namely, optimal water utilization. The numerical results for the surface groundwater in particular indicated that while the irrigation canals recharge water to the aquifer during both dry and wet season, small amounts of discharge from the aquifers to the canals occur only during the wet season. The analysis of the groundwater balance also showed that the present available groundwater potential is not fully exploited by the farmers, especially during the dry periods of surface water shortage. In contrast, the adoption of an optimal conjunctive management scheme would ensure extra water availability for additional annual rice crops in the region.     

Sediment yield and soil erosion assessment by using empirical models for Shazand watershed,a semi-arid area in center of Iran

Natural Hazards - In Kuwait, the transport sector is facing a daily traffic congestion pandemic. The traffic congestion is significantly influencing the economy and obstructing the development and...     

湖南省区域群发性地质灾害预警预报系统的设计研究

文章提出地质灾害是在一定的地面孕灾背景下，受特定的气象因素诱发而形成的突发性地质事件。因此，文中详细阐述了在特定的孕灾背景条件下，建立地质灾害预报预警模型的方法，从而为建立湖南省区域群发性地质灾害预警预报系统奠定基础。     

A volcanic activity alert-level system for aviation: review of its development and application in Alaska

Avalanche warning services (AWS) are operated to protect communities and traffic lines in avalanche-prone regions of the Alps and other mountain ranges. In times of high avalanche danger, these services may decide to close roads or to evacuate settlements. Closing decisions are based on field observations, avalanche release statistics, and snow forecasts issued by weather services. Because of the spatial variability in the snowpack and the insufficient understanding of avalanche triggering mechanisms, closing decisions are characterized by large uncertainties and the information based on which AWS have to decide is always incomplete. In this paper, we illustrate how signal detection theory can be applied to make better use of the information at hand. The proposed framework allows the evaluation of past road closures and points to how the decision performance of AWS could be improved. To illustrate the proposed framework, we evaluate the decision performance of two AWS in Switzerland and discuss the advantages of such a formalized decision-making approach.     

珠江三角洲平原广东省佛山市顺德区土壤-蔬菜系统中Pb的健康安全预测预警

分析珠江三角洲顺德区208个蔬菜地表层土样、114个蔬菜样Pb的全量和38个表层土样Pb的形态含量,结果表明,土壤Pb平均值为44.3mg/kg,77.5%的土壤Pb含量超过广东省土壤背景值,蔬菜Pb超标率为74.6%。用2007年蔬菜土壤Pb的累积速率(1.02mg/kg),预测未来10年土壤Pb含量变化趋势,并分别以150、270、300和8580(mg/kg)为阈值对土壤中Pb进行预警,2007—2017年超过150mg/kg的土壤面积比例有所增加,而超过270mg/kg、300mg/kg的土壤面积比例不变。蔬菜Pb与土壤Pb的全量或有效量之间均存在"高原模式"。蔬菜Pb的空间分布表明,3种蔬菜Pb的高浓度主要位于工业比较发达的城镇,这与土壤Pb的空间分布大体一致。经蔬菜途径吸收Pb的THQ靶标危害系数不超过0.4。不同区域、家庭经济收入水平的THQ排序:THQ高THQ城市THQ中THQ农村THQ低,表明经济收入水平高的家庭经蔬菜途径摄入Pb的健康风险最高。     

浙江农业地质环境调查土壤样品中54种指标配套分析方案和分析质量监控系统

根据有关规定和标准,制定了<浙江省农业地质环境调查>项目土壤样品中54种指标的配套分析方案及分析质量监控系统,并完成全部土壤样品的分析测试,为项目提供了巨量的基础数据,取得了良好的应用效果.     

小流域水土资源优化配置线性规划数学模型的构建及求解——以陕南丹凤大南沟小流域为例

陕南地区位于秦岭山区,坡耕地面积大,降雨形成的坡面径流是当地水土流失的主导因子,通过合理配置当地土地资源,充分利用坡面径流资源,从而减少水土流失。以陕南大南沟小流域为研究对象,通过收集整理当地多年的降雨资料,借助GIS及Surfer等相关软件对不同坡度的坡地资源进行划分和统计,利用流域内水土资源之间的相互依存及彼此约束性,基于线性规划理论,通过构建、求解水土资源优化配置线性规划的数学模型,对小流域的水土资源进行优化配置,并用单纯形法对模型进行求解。通过对模型中相关参数的不断优化、调节,最终得出“以人定水田”“以水定田无旱无树”“以水定田无旱有树”3种水土资源的优化配置方案。通过优化配置即可达到水土保持的目的,同时也为后期土地规划等提