scholarly journals The application of Bayesian networks in natural hazard analyses

2013 ◽  
Vol 1 (5) ◽  
pp. 5805-5854
Author(s):  
K. Vogel ◽  
C. Riggelsen ◽  
O. Korup ◽  
F. Scherbaum
Keyword(s):  
Bayesian Networks ◽  
Bayesian Network ◽  
Domain Knowledge ◽  
Natural Hazard ◽  
Hazard Analysis ◽  
Flood Damage ◽  
Continuous Variables ◽  
Real World Data ◽  
Ground Motion Model ◽  
Hazard Assessments

Abstract. In natural hazards we face several uncertainties due to our lack of knowledge and/or the intrinsic randomness of the underlying natural processes. Nevertheless, deterministic analysis approaches are still widely used in natural hazard assessments, with the pitfall of underestimating the hazard with potentially disastrous consequences. In this paper we show that the Bayesian network approach offers a flexible framework for capturing and expressing a broad range of different uncertainties as those encountered in natural hazard assessments. Although well studied in theory, the application of Bayesian networks on real-world data is often not straightforward and requires specific tailoring and adaption of existing algorithms. We demonstrate by way of three case studies (a ground motion model for a seismic hazard analysis, a flood damage assessment, and a landslide susceptibility study) the applicability of Bayesian networks across different domains showcasing various properties and benefits of the Bayesian network framework. We offer suggestions as how to tackle practical problems arising along the way, mainly concentrating on the handling of continuous variables, missing observations, and the interaction of both. We stress that our networks are completely data-driven, although prior domain knowledge can be included if desired.

scholarly journals Bayesian network learning for natural hazard analyses

2014 ◽  
Vol 14 (9) ◽  
pp. 2605-2626 ◽  
Author(s):  
K. Vogel ◽  
C. Riggelsen ◽  
O. Korup ◽  
F. Scherbaum
Keyword(s):  
Bayesian Networks ◽  
Bayesian Network ◽  
Measurement Errors ◽  
Natural Hazard ◽  
Regional Scale ◽  
Flood Damage ◽  
Continuous Variables ◽  
Real World Data ◽  
Network Learning ◽  
Hazard Assessments

Abstract. Modern natural hazards research requires dealing with several uncertainties that arise from limited process knowledge, measurement errors, censored and incomplete observations, and the intrinsic randomness of the governing processes. Nevertheless, deterministic analyses are still widely used in quantitative hazard assessments despite the pitfall of misestimating the hazard and any ensuing risks. In this paper we show that Bayesian networks offer a flexible framework for capturing and expressing a broad range of uncertainties encountered in natural hazard assessments. Although Bayesian networks are well studied in theory, their application to real-world data is far from straightforward, and requires specific tailoring and adaptation of existing algorithms. We offer suggestions as how to tackle frequently arising problems in this context and mainly concentrate on the handling of continuous variables, incomplete data sets, and the interaction of both. By way of three case studies from earthquake, flood, and landslide research, we demonstrate the method of data-driven Bayesian network learning, and showcase the flexibility, applicability, and benefits of this approach. Our results offer fresh and partly counterintuitive insights into well-studied multivariate problems of earthquake-induced ground motion prediction, accurate flood damage quantification, and spatially explicit landslide prediction at the regional scale. In particular, we highlight how Bayesian networks help to express information flow and independence assumptions between candidate predictors. Such knowledge is pivotal in providing scientists and decision makers with well-informed strategies for selecting adequate predictor variables for quantitative natural hazard assessments.

scholarly journals Fraud Detection of Bulk Cargo Theft in Port Using Bayesian Network Models

2020 ◽  
Vol 10 (3) ◽  
pp. 1056
Author(s):  
Rongjia Song ◽  
Lei Huang ◽  
Weiping Cui ◽  
María Óskarsdóttir ◽  
Jan Vanthienen
Keyword(s):  
Bayesian Networks ◽  
Bayesian Network ◽  
Predictive Models ◽  
Domain Knowledge ◽  
Fraud Detection ◽  
Network Models ◽  
Risk Elements ◽  
Data Driven Approach ◽  
Binary Classifiers ◽  
Cargo Theft

The fraud detection of cargo theft has been a serious issue in ports for a long time. Traditional research in detecting theft risk is expert- and survey-based, which is not optimal for proactive prediction. As we move into a pervasive and ubiquitous paradigm, the implications of external environment and system behavior are continuously captured as multi-source data. Therefore, we propose a novel data-driven approach for formulating predictive models for detecting bulk cargo theft in ports. More specifically, we apply various feature-ranking methods and classification algorithms for selecting an effective feature set of relevant risk elements. Then, implicit Bayesian networks are derived with the features to graphically present the relationship with the risk elements of fraud. Thus, various binary classifiers are compared to derive a suitable predictive model, and Bayesian network performs best overall. The resulting Bayesian networks are then comparatively analyzed based on the outcomes of model validation and testing, as well as essential domain knowledge. The experimental results show that predictive models are effective, with both accuracy and recall values greater than 0.8. These predictive models are not only useful for understanding the dependency between relevant risk elements, but also for supporting the strategy optimization of risk management.

Application of Bayesian Networks in Multi-Hazard Safety Assessment of Nuclear Power Plants

2020 ◽  
Author(s):  
Varenya Kumar D. Mohan ◽  
Philip Vardon ◽  
James Daniell ◽  
Pierre Gehl ◽  
Andreas Schafer ◽  
...  
Keyword(s):  
Risk Assessment ◽  
Bayesian Networks ◽  
Bayesian Network ◽  
Nuclear Power ◽  
Power Plants ◽  
Nuclear Power Plants ◽  
Probability Distributions ◽  
Sensitivity Analyses ◽  
Continuous Variables ◽  
Safety Assessments

<p>Low probability events occurring in sequence, within a limited operational time (damage and recovery window between events), are a key consideration in multi-hazard safety assessments of nuclear power plants (NPPs). Cascading effects from hazards and associated event sequences could potentially have a significant impact on risk estimates. The Bayesian network can act as a framework to consider aforementioned statistical dependencies between various hazards in multi-risk analyses of nuclear power plants.</p><p>Within the EU project NARSIS (New Approach to Reactor Safety Improvements), a Bayesian network-based risk assessment framework was developed to perform multi-hazard risk assessment of NPPs.</p><p>The Bayesian network method was applied for an external-event related station blackout (SBO) scenario at a NPP. Earthquake, flooding, and tornado were among the hazards considered at a decommissioned NPP site location in Europe. Both hazard dependency in time as well as a cascading scenario was also considered. The hazards, their interactions and the fragilities of selected systems, structures and components within the nuclear power plant were represented in the network and their probability distributions were obtained based on the multi-hazard and fragility approaches adopted within the NARSIS project.</p><p>Sensitivity analyses in the network were used to identify key hazards and interactions. Most influential hazard combinations and ranges of intensity measures were identified through diagnostic inference in the network. Discretisation of continuous variables (hazard curves in this case) is a key aspect of performing inference in Bayesian networks. The effect of various levels of discretisation of hazard probability distributions was assessed, to identify suitable discretisations of hazard data.</p><p>This application demonstrates the use and advantages of the Bayesian network methodology, developed in the NARSIS project, for probabilistic safety assessments of NPPs.</p>

scholarly journals A Review of Inference Algorithms for Hybrid Bayesian Networks

2018 ◽  
Vol 62 ◽  
pp. 799-828 ◽  
Author(s):  
Antonio Salmerón ◽  
Rafael Rumí ◽  
Helge Langseth ◽  
Thomas D. Nielsen ◽  
Anders L. Madsen
Keyword(s):  
Bayesian Networks ◽  
Bayesian Network ◽  
Closed Form ◽  
Dynamic Bayesian Networks ◽  
Software Systems ◽  
Continuous Variables ◽  
Hybrid Bayesian Networks ◽  
Closed Form Solutions ◽  
Inference Algorithms ◽  
The Difference

Hybrid Bayesian networks have received an increasing attention during the last years. The difference with respect to standard Bayesian networks is that they can host discrete and continuous variables simultaneously, which extends the applicability of the Bayesian network framework in general. However, this extra feature also comes at a cost: inference in these types of models is computationally more challenging and the underlying models and updating procedures may not even support closed-form solutions. In this paper we provide an overview of the main trends and principled approaches for performing inference in hybrid Bayesian networks. The methods covered in the paper are organized and discussed according to their methodological basis. We consider how the methods have been extended and adapted to also include (hybrid) dynamic Bayesian networks, and we end with an overview of established software systems supporting inference in these types of models.

scholarly journals Learning Continuous Time Bayesian Networks in Non-stationary Domains

2018 ◽  
Author(s):  
Simone Villa ◽  
Fabio Stella
Keyword(s):  
Bayesian Networks ◽  
Bayesian Network ◽  
Real World ◽  
Continuous Time ◽  
Real World Data ◽  
Change Over Time ◽  
World Data ◽  
Continuous Time Bayesian Networks ◽  
Continuous Time Bayesian Network ◽  
Over Time

Non-stationary continuous time Bayesian networks are introduced. They allow the parents set of each node in a continuous time Bayesian network to change over time. Structural learning of nonstationary continuous time Bayesian networks is developed under different knowledge settings. A macroeconomic dataset is used to assess the effectiveness of learning non-stationary continuous time Bayesian networks from real-world data.

scholarly journals Learning Discrete Bayesian Networks from Continuous Data

2017 ◽  
Vol 59 ◽  
pp. 103-132 ◽  
Author(s):  
Yi-Chun Chen ◽  
Tim A. Wheeler ◽  
Mykel J. Kochenderfer
Keyword(s):  
Bayesian Networks ◽  
Bayesian Network ◽  
Structure Learning ◽  
Minimum Description Length ◽  
Real Data ◽  
Continuous Variables ◽  
Bayesian Network Structure ◽  
Bayesian Network Structure Learning ◽  
Accuracy Speed ◽  
Standard Techniques

Learning Bayesian networks from raw data can help provide insights into the relationships between variables. While real data often contains a mixture of discrete and continuous-valued variables, many Bayesian network structure learning algorithms assume all random variables are discrete. Thus, continuous variables are often discretized when learning a Bayesian network. However, the choice of discretization policy has significant impact on the accuracy, speed, and interpretability of the resulting models. This paper introduces a principled Bayesian discretization method for continuous variables in Bayesian networks with quadratic complexity instead of the cubic complexity of other standard techniques. Empirical demonstrations show that the proposed method is superior to the established minimum description length algorithm. In addition, this paper shows how to incorporate existing methods into the structure learning process to discretize all continuous variables and simultaneously learn Bayesian network structures.

scholarly journals A Unified View of Causal and Non-causal Feature Selection

2021 ◽  
Vol 15 (4) ◽  
pp. 1-46
Author(s):  
Kui Yu ◽  
Lin Liu ◽  
Jiuyong Li
Keyword(s):  
Feature Selection ◽  
Bayesian Network ◽  
Synthetic Data ◽  
Selection Methods ◽  
Bayesian Network Model ◽  
Real World Data ◽  
Feature Sets ◽  
Unified View ◽  
Optimal Feature ◽  
Different Levels

In this article, we aim to develop a unified view of causal and non-causal feature selection methods. The unified view will fill in the gap in the research of the relation between the two types of methods. Based on the Bayesian network framework and information theory, we first show that causal and non-causal feature selection methods share the same objective. That is to find the Markov blanket of a class attribute, the theoretically optimal feature set for classification. We then examine the assumptions made by causal and non-causal feature selection methods when searching for the optimal feature set, and unify the assumptions by mapping them to the restrictions on the structure of the Bayesian network model of the studied problem. We further analyze in detail how the structural assumptions lead to the different levels of approximations employed by the methods in their search, which then result in the approximations in the feature sets found by the methods with respect to the optimal feature set. With the unified view, we can interpret the output of non-causal methods from a causal perspective and derive the error bounds of both types of methods. Finally, we present practical understanding of the relation between causal and non-causal methods using extensive experiments with synthetic data and various types of real-world data.

Application of Bayesian Network in Safety Evaluation of Metro Construction

2013 ◽  
Vol 838-841 ◽  
pp. 1463-1468
Author(s):  
Xiang Ke Liu ◽  
Zhi Shen Wang ◽  
Hai Liang Wang ◽  
Jun Tao Wang
Keyword(s):  
Bayesian Networks ◽  
Bayesian Network ◽  
Posterior Probability ◽  
Fault Tree ◽  
Fault Tree Analysis ◽  
Safety Evaluation ◽  
Tree Analysis ◽  
Tunnel Blasting ◽  
Better Than

The paper introduced the Bayesian networks briefly and discussed the algorithm of transforming fault tree into Bayesian networks at first, then regarded the structures impaired caused by tunnel blasting construction as a example, introduced the built and calculated method of the Bayesian networks by matlab. Then assumed the probabilities of essential events, calculated the probability of top event and the posterior probability of each essential events by the Bayesian networks. After that the paper contrast the characteristics of fault tree analysis and the Bayesian networks, Identified that the Bayesian networks is better than fault tree analysis in safety evaluation in some case, and provided a valid way to assess risk in metro construction.

scholarly journals Modeling the City Distribution System Reliability with Bayesian Networks to Identify Influence Factors

2016 ◽  
Vol 2016 ◽  
pp. 1-9 ◽  
Author(s):  
Hao Zhang ◽  
Liyu Zhu ◽  
Shensi Xu
Keyword(s):  
Bayesian Networks ◽  
Bayesian Network ◽  
System Reliability ◽  
Distribution System ◽  
Complex Problem ◽  
Practical Significance ◽  
Correlation Degree ◽  
Urban Distribution ◽  
Distribution System Reliability ◽  
The City

Under the increasingly uncertain economic environment, the research on the reliability of urban distribution system has great practical significance for the integration of logistics and supply chain resources. This paper summarizes the factors that affect the city logistics distribution system. Starting from the research of factors that influence the reliability of city distribution system, further construction of city distribution system reliability influence model is built based on Bayesian networks. The complex problem is simplified by using the sub-Bayesian network, and an example is analyzed. In the calculation process, we combined the traditional Bayesian algorithm and the Expectation Maximization (EM) algorithm, which made the Bayesian model able to lay a more accurate foundation. The results show that the Bayesian network can accurately reflect the dynamic relationship among the factors affecting the reliability of urban distribution system. Moreover, by changing the prior probability of the node of the cause, the correlation degree between the variables that affect the successful distribution can be calculated. The results have significant practical significance on improving the quality of distribution, the level of distribution, and the efficiency of enterprises.

Sign in / Sign up

Export Citation Format

Share Document