Seismic fragility of reinforced concrete girder bridges using Bayesian belief network

Infrastructure owners and operators, or governmental agencies, need rapid screening tools to prioritize detailed risk assessment and retrofit resources allocation. This paper provides one such tool, for use by highway administrations, based on Bayesian belief network (BBN) and aimed at replacing so‐called generic or typological seismic fragility functions for reinforced concrete girder bridges. Resources for detailed assessments should be allocated to bridges with highest consequence of damage, for which site hazard, bridge fragility, and traffic data are needed. The proposed BBN based model is used to quantify seismic fragility of bridges based on data that can be obtained by visual inspection and engineering drawings. Results show that the predicted fragilities are of sufficient accuracy for establishing relative ranking and prioritizing. While the actual data and seismic hazard employed to train the network (establishing conditional probability tables) refer to the Italian bridge stock, the network structure and engineering judgment can easily be adopted for bridges in different geographical locations. Copyright © 2015 John Wiley & Sons, Ltd.     

Applying Bayesian belief networks to health risk assessment

The health risk of noncarcinogenic substances is usually represented by the hazard quotient (HQ) or target organ-specific hazard index (TOSHI). However, three problems arise from these indicators. Firstly, the HQ overestimates the health risk of noncarcinogenic substances for non-critical organs. Secondly, the TOSHI makes inappropriately the additive assumption for multiple hazardous substances affecting the same organ. Thirdly, uncertainty of the TOSHI undermines the accuracy of risk characterization. To address these issues, this article proposes the use of Bayesian belief networks (BBN) for health risk assessment (HRA) and the procedure involved is developed using the example of road constructions. According to epidemiological studies and using actual hospital attendance records, the BBN-HRA can specifically identify the probabilistic relationship between an air pollutant and each of its induced disease, which can overcome the overestimation of the HQ for non-critical organs. A fusion technique of conditional probabilities in the BBN-HRA is devised to avoid the unrealistic additive assumption. The use of the BBN-HRA is easy even for those without HRA knowledge. The input of pollution concentrations into the model will bring more concrete information on the morbidity and mortality rates of all the related diseases rather than a single score, which can reduce the uncertainty of the TOSHI.     

A study of anthropogenic and climatic disturbance of the New River Estuary using a Bayesian belief network

The present paper utilizes a Bayesian Belief Network (BBN) approach to intuitively present and quantify our current understanding of the complex physical, chemical, and biological processes that lead to eutrophication in an estuarine ecosystem (New River Estuary, North Carolina, USA). The model is further used to explore the effects of plausible future climatic and nutrient pollution management scenarios on water quality indicators. The BBN, through visualizing the structure of the network, facilitates knowledge communication with managers/stakeholders who might not be experts in the underlying scientific disciplines. Moreover, the developed structure of the BBN is transferable to other comparable estuaries. The BBN nodes are discretized exploring a new approach called moment matching method. The conditional probability tables of the variables are driven by a large dataset (four years). Our results show interaction among various predictors and their impact on water quality indicators. The synergistic effects caution future management actions.     

A comparison of methods for spatial relative risk mapping of human neural tube defects

Birth defects are a major cause of infant mortality and disability in many parts of the world. Yet the etiology of neural tube defects (NTDs), the most common types of birth defects, is still unknown. The construction and analysis of maps of disease incidence data can help explain the geographical distribution of NTDs and can point to possible environmental causes of these birth defects. We compared two methods of mapping spatial relative risk of NTDs: (1) hierarchical Bayesian model, and (2) Spatial filtering method. Heshun county, which has the highest rate of NTDs in China, was selected as the region of interest. Both methods were used to produce a risk map of NTDs for rural Heshun for 1998–2001. Hierarchical Bayesian model estimated the relative risk for any given village in Heshun by “borrowing” strength from other villages in the study region. It did not remove all the random spatial noise in the rude disease rate. There were several areas of high incidence scattered around its risk map with no readily apparent pattern. The spatial filtering method calculated the relative risk for all villages based on a series of circulars. The risk map from the spatial filtering method revealed some spatial clusters of NTDs in Heshun. These two methods differed in their ability to map the spatial relative risk of NTDs. Distributional assumption of relative risk and the target of the risk assessment should be taken into consideration when choosing which method to use.     

Stochastic ground motion models to NGA-West2 and NGA-Sub databases using Bayesian neural network

Ground motion models (GMMs) are traditionally developed from a frequentist approach. The Bayesian framework has received recent attention in developing nonergodic models, measuring uncertainty, or updating the model with additional data. However, no neural networks are developed to date in this framework to predict ground motion parameters or spectra. Hence, the present work develops a probabilistic Bayesian neural network (PBNN) to next-generation attenuation – West2 and Subduction databases using variational inference with mean-field assumption. Network inputs are magnitude, rupture distance, hypocentral depth, shear wave velocity, style of faulting, and region flags; outputs are peak ground values and response spectra. Both models have two hidden layers with seven neurons in each hidden layer. The models are verified for potential overfit, and their performance is validated through the parametric study by varying inputs. The output of a deterministic model is a point estimate. Considering probabilistic layers in hidden and output layers enables the model to capture within-model epistemic uncertainty and aleatory variability. Obtained aleatory standard deviations are consistent with other models. Mean epistemic uncertainty and aleatory variability are in the range 0.07–0.10 and 0.62–0.78 (ln units) for NGA-West2 and 0.09–0.16 and 0.67–0.95 for NGA-Sub models, respectively. The correlation coefficients between recorded and overall mean predictions ranged from 0.94 to 0.97 for NGA-the West2 model and from 0.91 to 0.95 for the NGA-Sub models. Network performance for out-of-training inputs showed increased epistemic deviations with no effect on aleatory deviations.     

Risk assessment using suprema data

This paper proposes a stochastic approach to model temperature dynamic and study related risk measures. The dynamic of temperatures can be modelled by a mean-reverting process such as an Ornstein–Uhlenbeck one. In this study, we estimate the parameters of this process thanks to daily observed suprema of temperatures, which are the only data gathered by some weather stations. The expression of the cumulative distribution function of the supremum is obtained thanks to the law of the hitting time. The parameters are estimated by a least square method quantiles based on this function. Theoretical results, including mixing property and consistency of model parameters estimation, are provided. The parameters estimation is assessed on simulated data and performed on real ones. Numerical illustrations are given for both data. This estimation will allow us to estimate risk measures, such as the probability of heat wave and the mean duration of an heat wave.     

Using a Bayesian belief network model for early warning of death and severe risk of HFMD in Hunan province,China

Hand, foot, and mouth disease (HFMD) is a global infectious disease resulting in millions of cases and even hundreds of deaths. Although a newly developed formalin-inactivated EV71 (FI-EV71) vaccine is effective against EV71, which is a major pathogen for HFMD, no vaccine against HFMD itself has yet been developed. Therefore, establishing a sensitive and accurate early warning system for HFMD is important. The early warning model for HFMD in the China Infectious Disease Automated-alert and Response System combines control chart and spatial statistics models to detect spatiotemporal abnormal aggregations of morbidity. However, that type of early warning for HFMD just involves retrospective analysis. In this study, we apply a Bayesian belief network (BBN) to estimate the increased risk of death and severe HFMD in the next month based on pathogen detection and environmental factors. Hunan province, one of the regions with the highest prevalence of HFMD in China, was selected as the study area. The results showed that compared with the traditional early warning model for HFMD, the proposed method can achieve a very high performance evaluation (the average AUC tests were more than 0.92). The model is also simple and easy to operate. Once the structure of the BBN is established, the increased risk of death and severe HFMD in the next month can be estimated based on any one node in the BBN.     

概率神经网络技术在煤田地震反演中的应用研究

实现从构造勘探向岩性勘探阶段的转变,是煤田地震勘探亟待解决的重要问题。其中,地震反演技术是岩性勘探的一种重要手段。为了规避常规反演方法的固有限制,利用概率神经网络技术预测井数据和地震数据之间的非线性关系,得到密度数据体和速度数据体,并获得相应的波阻抗数据体。对某矿区的实际地震资料采用该技术进行岩性反演,得到了较为准确的波阻抗数据体,为岩性解释提供了不可或缺的资料。     

基于LSTM网络的单台仪器地震烈度预测模型

烈度是地震预警系统的关键产出.如何实现快速预测目标场址的地震烈度是地震预警方法技术研究中的核心问题.本文提出了一种基于长短时记忆神经网络(Long Short-Term Memory, LSTM)的单台仪器地震烈度的预测模型(LSTM-Ⅰ).该模型以一个台站观测到地震动参数的时间序列特征为输入, 实现动态预测该台站可能遭受的最大烈度.选取了日本K-NET台网记录的102次地震的5103条强震加速度记录训练了神经网络, 利用89次地震的3781条数据检验了模型的泛化能力.利用准确率、漏报率以及误报率三个评价指标评价了LSTM-Ⅰ模型的性能.结果表明, 当采用P波触发后3 s的序列进行预测时, 模型出现漏报的概率为46.78%, 出现误报的概率为1.25%;当采用P波触发后10 s的序列进行预测时, 模型出现漏报的概率大幅降低到17.6%, 出现误报的概率降低到1.14%.结果表明LSTM-Ⅰ模型很好把握住了时间序列中蕴含的特征.进一步基于LSTM-Ⅰ模型评估了Ⅵ度下台站所能提供的预警时间.本文模型能够提供的预警时间与P-S波到时差接近, 说明LSTM-Ⅰ模型具有较高的时效性.

     

Nonlinear inversion of electrical resistivity imaging using pruning Bayesian neural networks

Conventional artificial neural networks used to solve electrical resistivity imaging (ERI) inversion problem suffer from overfitting and local minima. To solve these problems, we propose to use a pruning Bayesian neural network (PBNN) nonlinear inversion method and a sample design method based on the K-medoids clustering algorithm. In the sample design method, the training samples of the neural network are designed according to the prior information provided by the K-medoids clustering results; thus, the training process of the neural network is well guided. The proposed PBNN, based on Bayesian regularization, is used to select the hidden layer structure by assessing the effect of each hidden neuron to the inversion results. Then, the hyperparameter α _k , which is based on the generalized mean, is chosen to guide the pruning process according to the prior distribution of the training samples under the small-sample condition. The proposed algorithm is more efficient than other common adaptive regularization methods in geophysics. The inversion of synthetic data and field data suggests that the proposed method suppresses the noise in the neural network training stage and enhances the generalization. The inversion results with the proposed method are better than those of the BPNN, RBFNN, and RRBFNN inversion methods as well as the conventional least squares inversion.     

3-D inversion of borehole-to-surface electrical data using a back-propagation neural network

The “fluid-flow tomography”, an advanced technique for geoelectrical survey based on the conventional mise-à-la-masse measurement, has been developed by Exploration Geophysics Laboratory at the Kyushu University. This technique is proposed to monitor fluid-flow behavior during water injection and production in a geothermal field. However data processing of this technique is very costly. In this light, this paper will discuss the solution to cost reduction by applying a neural network in the data processing. A case study in the Takigami geothermal field in Japan will be used to illustrate this. The achieved neural network in this case study is three-layered and feed-forward. The most successful learning algorithm in this network is the Resilient Propagation (RPROP). Consequently, the study advances the pragmatism of the “fluid-flow tomography” technique which can be widely used for geothermal fields. Accuracy of the solution is then verified by using root mean square (RMS) misfit error as an indicator.     

Modelling evaporation using an artificial neural network algorithm

This paper investigates the prediction of Class A pan evaporation using the artificial neural network (ANN) technique. The ANN back propagation algorithm has been evaluated for its applicability for predicting evaporation from minimum climatic data. Four combinations of input data were considered and the resulting values of evaporation were analysed and compared with those of existing models. The results from this study suggest that the neural computing technique could be employed successfully in modelling the evaporation process from the available climatic data set. However, an analysis of the residuals from the ANN models developed revealed that the models showed significant error in predictions during the validation, implying loss of generalization properties of ANN models unless trained carefully. The study indicated that evaporation values could be reasonably estimated using temperature data only through the ANN technique. This would be of much use in instances where data availability is limited. Copyright © 2002 John Wiley & Sons, Ltd.     

基于神经网络的结构震后快速损伤评估

为了利用结构地震响应观测数据在震后对结构进行损伤快速评估,本文提出了基于BP传播神经网络多参数预测震后结构损伤程度的方法。本文设计了9个不同设防烈度和层数的钢筋混凝土框架结构,利用OpenSees有限元软件进行了非线性时程分析,并用损伤指数量化了结构损伤程度。利用有限元模拟结果,创建了神经网络的数据集,训练神经网络建立了结构参数与结构损伤指数之间的映射,对比了不同参数组合预测结构损伤水平的能力,提出了最优参数组合。结果表明：此方法预测结构损伤指数准确度高,耗时短,可为建筑工程震后损伤快速评估提供支撑。     

Identification of pulse-like ground motions using artificial neural network

For more than 20 years, the concept of near-fault pulse-like ground motion has been a topic of great interest due to its distinct characteristics, particularly due to directivity or fling effects, which are hugely influenced by the rupture mechanism. These unexpected characteristics, along with their effective frequency, energy rate, and damage indices, create a near-fault, pulse-like ground motion capable of causing severe damage to structures. One of the most common approaches for identifying ...     

Using spatial multilevel regression analysis to assess soil type contextual effects on neural tube defects

The rate of neural tube defects (NTDs) in Shanxi Province is the highest world widely. Both human and environmental factors can induce NTDs, but various studies ignored contextual effects. This research examines whether there are significant soil type contextual effects on the rate of NTDs. A spatial two-level regression model is used to quantify the magnitude of contextual effects. Spatial autocorrelated errors structure is used to control autocorrelation of residuals. The results suggest that the spatial multilevel model fit the data better than non-spatial multilevel models. Our findings indicate that there are significant soil type contextual effects on the rate of NTDs, even after taking into account of fertilizer and net income. More attentions should be focused on how characteristics of each soil type may affect the rates of NTDs in further studies, which is a relevant issue for understanding etiology of NTDs.     

Risk evaluation of heavy snow disasters using BP artificial neural network: the case of Xilingol in Inner Mongolia

According to disaster and risk evaluation theory, we proposed an indicator system containing environmental possibilities with hazard, disaster inducing factors and disaster bearing bodies to analyze the risk of heavy snow disaster in Xilingol, Inner Mongolia, based on the analysis of heavy snow events that have occurred in the last several decades. A risk evaluation model of heavy snow disaster was established using back-propagation artificial neural network (BP-ANN). Data obtained from a number of heavy snow events samples were used to train artificial neural network (ANN). The objective of this study is to produce a new evaluation model using BP-ANN for heavy snow risk analysis. As a result, BP-ANN model showed an advantage in heavy snow risk evaluation in Xilingol compared to the conventional method of evaluation criteria equation (ECE) introduced by Inner Mongolia Municipality Animal Husbandry Bureau. Thus, the BP-ANN model provides an alternative method for heavy snow risk analysis in the area.     

电阻率二维神经网络反演

由于非线性特性地球物理反演一直以来都是一个比较困难的问题. 近十年来,非线性反演方法如人工神经网络、遗传算法在地球物理数据解释中得到越来越多的应用,但目前基本仍限于一维反演问题. 对于二维反问题,反演参数较多,神经网络反演运用较少. 本文利用BP神经网络优化方法,实现了电阻率二维非线性反演. 与传统线性化的迭代反演比较,神经网络反演能够克服传统方法的不足、获得更好的反演结果.     

Landslide susceptibility analysis using GIS and artificial neural network

The purpose of this study is to develop landslide susceptibility analysis techniques using an arti?cial neural network and to apply the newly developed techniques to the study area of Yongin in Korea. Landslide locations were identi?ed in the study area from interpretation of aerial photographs, ?eld survey data, and a spatial database of the topography, soil type and timber cover. The landslide‐related factors (slope, curvature, soil texture, soil drainage, soil effective thickness, timber age, and timber diameter) were extracted from the spatial database. Using those factors, landslide susceptibility was analysed by arti?cial neural network methods. The landslide susceptibility index was calculated by the back‐propagation method, which is a type of arti?cial neural network method, and the susceptibility map was made with a geographic information system (GIS) program. The results of the landslide susceptibility analysis were veri?ed using landslide location data. The validation results showed satisfactory agreement between the susceptibility map and the existing data on landslide location. A GIS was used to ef?ciently analyse the vast amount of data, and an arti?cial neural network to be an effective tool to maintain precision and accuracy. The results can be used to reduce hazards associated with landslides and to plan land use and construction. Copyright © 2003 John Wiley & Sons, Ltd.     

Indian summer monsoon rainfall prediction using artificial neural network

Forecasting the monsoon temporally is a major scientific issue in the field of monsoon meteorology. The ensemble of statistics and mathematics has increased the accuracy of forecasting of Indian summer monsoon rainfall (ISMR) up to some extent. But due to the nonlinear nature of ISMR, its forecasting accuracy is still below the satisfactory level. Mathematical and statistical models require complex computing power. Therefore, many researchers have paid attention to apply artificial neural network in ISMR forecasting. In this study, we have used feed-forward back-propagation neural network algorithm for ISMR forecasting. Based on this algorithm, we have proposed the five neural network architectures designated as BP1, BP2, $\ldots, $ … , BP5 using three layers of neurons (one input layer, one hidden layer and one output layer). Detail architecture of the neural networks is provided in this article. Time series data set of ISMR is obtained from Pathasarathy et al. (Theor Appl Climatol 49:217–224 1994) (1871–1994) and IITM (http://www.tropmet.res.in/, 2012) (1995–2010) for the period 1871–2010, for the months of June, July, August and September individually, and for the monsoon season (sum of June, July, August and September). The data set is trained and tested separately for each of the neural network architecture, viz., BP1–BP5. The forecasted results obtained for the training and testing data are then compared with existing model. Results clearly exhibit superiority of our model over the considered existing model. The seasonal rainfall values over India for next 5 years have also been predicted.     

利用卷积神经网络检测地震的方法与优化

本文以西昌台阵观测的8 321次近震数据为例,详细介绍了利用深度卷积神经网络检测地震的数据处理流程,包括数据预处理、模型训练、波形长度、网络层数、学习率和概率阈值等关键参数对检测结果的影响,并将训练得到的最优模型,应用于事件波形和连续波形的检测。研究表明,数据预处理和数据增强可以提升模型的检测精度和抗干扰能力。用于模型训练的波形窗口长度可近似于S-P到时差的最大值。不同网络层数(5—8层)的检测结果差别不大。对于地震检测,学习率设为10-4—10-3较为合适。卷积神经网络检测出的地震数量与选择的概率阈值有关,通过绘制精确率-召回率变化曲线,可以为选择合适的概率阈值提供参考。本文为进一步利用深度学习算法提高地震检测效果提供了参考。