A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Machine Learning-Based Risk Analysis for Infrastructure Vulnerable to Flood Hazards
Flood hazards have affected millions of people through damage to infrastructure. Flood hazards in the Great Lakes area in recent years have caused a large area of the infrastructure system in Indiana and Illinois to be paralyzed due to the impact of the high flood level on infrastructure. To assess the risk of floods for certain types of infrastructure, we develop a machine learning-based risk analysis model to generate predictions of risk scores based on several indicators from a public dataset. Different infrastructure types such as bridges, culverts, pump stations, and roads were considered. We predicted risk scores to represent the flood risk from multiple components, such as exposure and criticality to flood hazards. The correlation between certain indicators and risk scores was examined to determine the critical variables used as input for the risk analysis model. The Gaussian process regression (GPR) algorithm was applied to train and test the dataset. From the analysis results, we find the GPR model provides accurate prediction. Therefore, the machine learning-based risk analysis is a valid approach to identify the degree to which infrastructure assets are at risk and provide stakeholders and decision-makers with the suggestions on minimizing the effects of future flood events.
Machine Learning-Based Risk Analysis for Infrastructure Vulnerable to Flood Hazards
Flood hazards have affected millions of people through damage to infrastructure. Flood hazards in the Great Lakes area in recent years have caused a large area of the infrastructure system in Indiana and Illinois to be paralyzed due to the impact of the high flood level on infrastructure. To assess the risk of floods for certain types of infrastructure, we develop a machine learning-based risk analysis model to generate predictions of risk scores based on several indicators from a public dataset. Different infrastructure types such as bridges, culverts, pump stations, and roads were considered. We predicted risk scores to represent the flood risk from multiple components, such as exposure and criticality to flood hazards. The correlation between certain indicators and risk scores was examined to determine the critical variables used as input for the risk analysis model. The Gaussian process regression (GPR) algorithm was applied to train and test the dataset. From the analysis results, we find the GPR model provides accurate prediction. Therefore, the machine learning-based risk analysis is a valid approach to identify the degree to which infrastructure assets are at risk and provide stakeholders and decision-makers with the suggestions on minimizing the effects of future flood events.
Machine Learning-Based Risk Analysis for Infrastructure Vulnerable to Flood Hazards
Duan, Junyi (author) / Gao, Joy (author) / Tao, Chengcheng (author)
Construction Research Congress 2024 ; 2024 ; Des Moines, Iowa
2024-03-18
Conference paper
Electronic Resource
English
| British Library Conference Proceedings | 1999
| Taylor & Francis Verlag | 1980
Managing Flood Risk on Railway Infrastructure
| British Library Conference Proceedings | 2004