High‐resolution flood probability mapping using generative machine learning with large‐scale synthetic precipitation and inundation data DOI Creative Commons
Lipai Huang, Federico Antolini, Ali Mostafavi

et al.

Computer-Aided Civil and Infrastructure Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: April 23, 2025

Abstract High‐resolution flood probability maps are instrumental for assessing risk but often limited by the availability of historical data. Additionally, producing simulated data needed creating probabilistic using physics‐based models involves significant computation and time effort, which inhibit its feasibility. To address this gap, study introduces Precipitation‐Flood Depth Generative Pipeline, a novel methodology that leverages generative machine learning to generate large‐scale synthetic inundation produce maps. With focus on Harris County, Texas, Pipeline begins with training cell‐wise depth estimator number precipitation‐flood events model model. This estimator, emphasizes precipitation‐based features, outperforms universal models. Subsequently, conditional adversarial network (CTGAN) is used conditionally precipitation point cloud, filtered strategic thresholds align realistic patterns. Hence, feature pool constructed each cell, enabling sampling generation events. After generating 10,000 events, created various depths. Validation similarity correlation metrics confirms accuracy distributions. The provides scalable solution high‐resolution maps, can enhance mitigation planning.

Language: Английский

SPN-Based Dynamic Risk Modeling of Fire Incidents in a Smart City DOI Creative Commons

Menghan Hui,

Feng Ni, Wencheng Liu

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(5), P. 2701 - 2701

Published: March 3, 2025

Smart cities are confronted with a variety of disaster threats. Among them, natural fires pose serious threat to human lives, the environment, and asset security. In view fact that existing research mostly focuses on analysis accident precursors, this paper proposes dynamic risk-modeling method based Stochastic Petri Nets (SPN) Bayesian theory deeply explore evolution mechanism urban fires. The SPN model is constructed through language processing techniques, which discretize process. Then, introduced dynamically update parameters, enabling accurate assessment key event nodes. results show can effectively identify high-risk nodes in Their probabilities increase significantly over time, transition have remarkable impact emergency response efficiency. This fire prevention control efficiency by approximately 30% reduce potential losses more than 20%. improves accuracy risk prediction integrating real-time observation data provides quantitative support for decision making. It recommended management departments focus strengthening maintenance facilities areas (such as alarm systems passages), optimize cross-departmental cooperation processes, build an intelligent monitoring early-warning system shorten time. study new theoretical tool management. future, it be extended other types disasters enhance universality model.

Language: Английский

Citations

0
Development of a real-time dynamic inundation risk assessment approach on paddy fields during typhoons: Exploration of adaptation strategies and quantification of risks DOI
Bing-Chen Jhong, Foong Ling Chen, Ching‐Pin Tung

et al.

Journal of Environmental Management, Journal Year: 2025, Volume and Issue: 380, P. 124981 - 124981

Published: March 13, 2025

Language: Английский

Citations

0
A comprehensive review of flood monitoring and evaluation in Nigeria DOI

Babati Abu-hanifa,

Auwal F. Abdussalam, Saadatu Umaru Baba

et al.

International Journal of Energy and Water Resources, Journal Year: 2025, Volume and Issue: unknown

Published: April 8, 2025

Language: Английский

Citations

0
High‐resolution flood probability mapping using generative machine learning with large‐scale synthetic precipitation and inundation data DOI Creative Commons
Lipai Huang, Federico Antolini, Ali Mostafavi

et al.

Computer-Aided Civil and Infrastructure Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: April 23, 2025

Abstract High‐resolution flood probability maps are instrumental for assessing risk but often limited by the availability of historical data. Additionally, producing simulated data needed creating probabilistic using physics‐based models involves significant computation and time effort, which inhibit its feasibility. To address this gap, study introduces Precipitation‐Flood Depth Generative Pipeline, a novel methodology that leverages generative machine learning to generate large‐scale synthetic inundation produce maps. With focus on Harris County, Texas, Pipeline begins with training cell‐wise depth estimator number precipitation‐flood events model model. This estimator, emphasizes precipitation‐based features, outperforms universal models. Subsequently, conditional adversarial network (CTGAN) is used conditionally precipitation point cloud, filtered strategic thresholds align realistic patterns. Hence, feature pool constructed each cell, enabling sampling generation events. After generating 10,000 events, created various depths. Validation similarity correlation metrics confirms accuracy distributions. The provides scalable solution high‐resolution maps, can enhance mitigation planning.

Language: Английский

Citations

0