Early warning of water quality degradation: A copula-based Bayesian network model for highly efficient water quality risk assessment

2021 ◽  
Vol 292 ◽  
pp. 112749
Author(s):  
Ruolan Yu ◽  
Chen Zhang
Keyword(s):  
Water Quality ◽  
Risk Assessment ◽  
Bayesian Network ◽  
Network Model ◽  
Early Warning ◽  
Bayesian Network Model ◽  
Highly Efficient ◽  
Quality Degradation ◽  
Quality Risk

scholarly journals A spatial Bayesian network model to assess the benefits of early warning for urban flood risk to people

2016 ◽  
Vol 16 (6) ◽  
pp. 1323-1337 ◽  
Author(s):  
Stefano Balbi ◽  
Ferdinando Villa ◽  
Vahid Mojtahed ◽  
Karin Tessa Hegetschweiler ◽  
Carlo Giupponi
Keyword(s):  
Bayesian Network ◽  
Network Model ◽  
Early Warning ◽  
Flood Risk ◽  
Human Impacts ◽  
Probability Distributions ◽  
Warning System ◽  
Post Traumatic Stress ◽  
Bayesian Network Model ◽  
Urban Flood

Abstract. This article presents a novel methodology to assess flood risk to people by integrating people's vulnerability and ability to cushion hazards through coping and adapting. The proposed approach extends traditional risk assessments beyond material damages; complements quantitative and semi-quantitative data with subjective and local knowledge, improving the use of commonly available information; and produces estimates of model uncertainty by providing probability distributions for all of its outputs. Flood risk to people is modeled using a spatially explicit Bayesian network model calibrated on expert opinion. Risk is assessed in terms of (1) likelihood of non-fatal physical injury, (2) likelihood of post-traumatic stress disorder and (3) likelihood of death. The study area covers the lower part of the Sihl valley (Switzerland) including the city of Zurich. The model is used to estimate the effect of improving an existing early warning system, taking into account the reliability, lead time and scope (i.e., coverage of people reached by the warning). Model results indicate that the potential benefits of an improved early warning in terms of avoided human impacts are particularly relevant in case of a major flood event.

An Artificial Neural Network and Bayesian Network model for liquidity risk assessment in banking

2018 ◽  
Vol 275 ◽  
pp. 2525-2554 ◽  
Author(s):  
Madjid Tavana ◽  
Amir-Reza Abtahi ◽  
Debora Di Caprio ◽  
Maryam Poortarigh
Keyword(s):  
Neural Network ◽  
Risk Assessment ◽  
Artificial Neural Network ◽  
Bayesian Network ◽  
Network Model ◽  
Liquidity Risk ◽  
Bayesian Network Model ◽  
Artificial Neural

scholarly journals Information Security Risk Assessment of Smartphones Using Bayesian Networks

2015 ◽  
Author(s):  
Kristian Herland ◽  
Heikki Hämmäinen ◽  
Pekka Kekolahti
Keyword(s):  
Risk Assessment ◽  
Information Security ◽  
Bayesian Networks ◽  
Bayesian Network ◽  
Network Model ◽  
Security Risk ◽  
Bayesian Network Model ◽  
Information Security Risk ◽  
Security Risk Assessment ◽  
Causal Bayesian Network

This study comprises an information security risk assessment of smartphone use in Finland using Bayesian networks. The primary research method is a knowledge-based approach to build a causal Bayesian network model of information security risks and consequences. The risks, consequences, probabilities and impacts are identified from domain experts in a 2-stage interview process with 8 experts as well as from existing research and statistics. This information is then used to construct a Bayesian network model which lends itself to different use cases such as sensitivity and scenario analysis. The identified risks’probabilities follow a long tail wherein the most probable risks include unintentional data disclosure, failures of device or network, shoulder surfing or eavesdropping and loss or theft of device. Experts believe that almost 50% of users share more information to other parties through their smartphones than they acknowledge or would be willing to share. This study contains several implications for consumers as well as indicates a clear need for increasing security awareness among smartphone users.  

scholarly journals A spatial Bayesian network model to assess the benefits of early warning for urban flood risk to people

2015 ◽  
Vol 3 (10) ◽  
pp. 6615-6649 ◽  
Author(s):  
S. Balbi ◽  
F. Villa ◽  
V. Mojtahed ◽  
K. T. Hegetschweiler ◽  
C. Giupponi
Keyword(s):  
Bayesian Network ◽  
Network Model ◽  
Early Warning ◽  
Traumatic Stress ◽  
Flood Risk ◽  
Human Impacts ◽  
Stress Disorders ◽  
Post Traumatic Stress ◽  
Bayesian Network Model ◽  
Post Traumatic

Abstract. This article presents a novel methodology to assess flood risk to people by integrating people's vulnerability and ability to cushion hazards through coping and adapting. The proposed approach extends traditional risk assessments beyond material damages; complements quantitative and semi-quantitative data with subjective and local knowledge, improving the use of commonly available information; produces estimates of model uncertainty by providing probability distributions for all of its outputs. Flood risk to people is modeled using a spatially explicit Bayesian network model calibrated on expert opinion. Risk is assessed in terms of: (1) likelihood of non-fatal physical injury; (2) likelihood of post-traumatic stress disorder; (3) likelihood of death. The study area covers the lower part of the Sihl valley (Switzerland) including the city of Zurich. The model is used to estimate the benefits of improving an existing Early Warning System, taking into account the reliability, lead-time and scope (i.e. coverage of people reached by the warning). Model results indicate that the potential benefits of an improved early warning in terms of avoided human impacts are particularly relevant in case of a major flood event: about 75 % of fatalities, 25 % of injuries and 18 % of post-traumatic stress disorders could be avoided.

Sign in / Sign up

Export Citation Format

Share Document