Parameterisation and evaluation of a Bayesian network for use in an ecological risk assessment

Pollino, Carmel; Woodberry, Owen; Nicholson, Ann E.; Korb, Kevin B.; Hart, Barry T.

doi:10.1016/j.envsoft.2006.03.006

Cited by 400 publications

(289 citation statements)

References 16 publications

Supporting

Mentioning

284

Contrasting

Unclassified

Order By: Relevance

“…During the interviews, participants are asked questions similar to the following: "Given information about the state of node X's parents, what is the probability that variable X takes state i?" (Pollino et al 2007b). This series of questions continues until all possible combinations of system states are exhausted.…”

Section: Conditional Probability Tables (Cpts)mentioning

confidence: 99%

Bayesian Networks for Modeling Dredging Decisions

Schultz¹,

Borrowman²,

Small³

2011

View full text Add to dashboard Cite

Section: Conditional Probability Tables (Cpts)mentioning

confidence: 99%

Bayesian Networks for Modeling Dredging Decisions

Schultz¹,

Borrowman²,

Small³

2011

View full text Add to dashboard Cite

“…Given that this is a pure quantitative BN model, its evaluation should include assessments of predictive accuracy and sensitivity analysis. Predictive accuracy refers to a quantitative evaluation of the model, by comparing model predictions with observed data [62].…”

Section: Consistency and Quality Assessment Of The Bns Model And Itsmentioning

confidence: 99%

Innovative Analysis of Runoff Temporal Behavior through Bayesian Networks

Molina

Zazo

Rodríguez‐Gonzálvez

et al. 2016

Water

View full text Add to dashboard Cite

Hydrological series are largely characterized by a strong random component in their behavior. More noticeable changes in the behavior patterns of rainfall/runoff temporal series are recently being observed. These modifications are not a trivial issue, especially in regards to peculiarities, non-linearities, diffused influences or higher time orders of dependence. This study mainly aimed to analyze the temporal dependence of an annual runoff series dynamically. This approach comprises a coupling between classic techniques (Autoregressive Moving Average Model, ARMA) and novel ones, based on Artificial Intelligent for hydrological research (Bayesian Networks, BNs). An ARMA model was built to provide reliable data to populate BNs. Then, causal reasoning, through Bayes's theorem, allows the identification of the logic structure of temporal dependences within time series. Furthermore, the resultant conditional probability permits the quantification of the relative percentage of annual runoff change, and provides the right time order of dependence. This research introduces an original methodology able to build a logic structure for a stochastic analysis of temporal behavior. This approach also aimed to provide a powerful and graphic modeling method for improving the understanding of the dynamic runoff series temporal behavior. This was successfully demonstrated in two unregulated river basin stretches, belonging to the Duero river basin which is the largest basin in Spain.

show abstract

“…The conditional probabilities can also be determined by a combination of methods. For example, expert probabilities can be combined with observational data to describe outcomes of extreme events not represented in the dataset (Pollino et al, 2007). If no data is available, the values will need to be assigned through expert judgment, and when objective data become available, this can then update or replace any estimates that have been entered into the model using subjective means.…”

Section: Situation Modelingmentioning

confidence: 99%

“…The first level is to ensure that key objects and their relationships have been represented in the model, and the second level should review the determined states to ensure that they have been defined unambiguously. There are three evaluation methods to validate the performance of a model: sensitivity analysis, data-based evaluation and non-quantitative evaluation of model outputs using experts (Pollino et al, 2007). In the event that large data sets are not available, and the probabilities must be elicited from domain experts, the sensitivity analysis technique is often used to investigate the effect of probability parameter changes on the performance of BNs.…”

Section: Situation Evaluationmentioning

confidence: 99%

A situation risk awareness approach for process systems safety

Naderpour

Zhang

2014

Safety Science

View full text Add to dashboard Cite

Abstract:Promoting situation awareness is an important design objective for a wide variety of domains, especially for process systems where the information flow is quite high and poor decisions may lead to serious consequences. In today"s process systems, operators are often moved to a control room far away from the physical environment, and increasing amounts of information are passed to them via automated systems, they therefore need a greater level of support to control and maintain the facilities in safe conditions. This paper proposes a situation risk awareness approach for process systems safety where the effect of ever-increasing situational complexity on human decision-makers is a concern. To develop the approach, two important aspects -addressing hazards that arise from hardware failure and reducing human error through decision-making -have been considered. The proposed situation risk awareness approach includes two major elements: an evidence preparation component and a situation assessment component. The evidence preparation component provides the soft evidence, using a fuzzy partitioning method, that is used in the subsequent situation assessment component. The situation assessment component includes a situational network based on dynamic Bayesian networks to model the abnormal situations, and a fuzzy risk estimation method to generate the assessment result. A case from U.S. Chemical Safety Board investigation reports has been used to illustrate the application of the proposed approach.

show abstract

Parameterisation and evaluation of a Bayesian network for use in an ecological risk assessment

Cited by 400 publications

References 16 publications

Bayesian Networks for Modeling Dredging Decisions

Bayesian Networks for Modeling Dredging Decisions

Innovative Analysis of Runoff Temporal Behavior through Bayesian Networks

A situation risk awareness approach for process systems safety

Contact Info

Product

Resources

About