Hierarchical Bayesian Network Based Incremental Model for Flood Prediction

Wu, Yirui; Xu, Weigang; Yu, Qinghan; Feng, Jun; Lü, Tong

doi:10.1007/978-3-030-05710-7_46

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sub-unit division involves the partitioning of the entire basin into multiple units to consider uneven rainfall distribution and facilitate consideration of variations in underlying surface conditions. Water source separation entails dividing the runoff into three components: surface, soil, and underground [37]. These three water sources possess varying confluence velocities, with the surface having the fastest and the underground the slowest.…”

Section: Datasetsmentioning

confidence: 99%

A Multiple Model Approach for Flood Forecasting, Simulation, and Evaluation Coupling in Zhouqu County

Li,

Liu,

Liu

et al. 2023

Water

View full text Add to dashboard Cite

Flood disasters are considered to be one of the ten natural disasters that threaten the survival of mankind. They occur frequently and have a serious impact on the national economy. For quicker response to the sudden flood, in this paper, the relevant characteristics of flood forecasting and disaster assessment are comprehensively studied to establish the corresponding models, and a multi-objective culture shuffled complex differential evolution (MOCSCDE) algorithm is proposed to optimize the model parameters. It can achieve better convergence and significantly improve the model accuracy. Then, a river hydrodynamic model is established to simulate the flooding process, and the characteristics of flood evolution, such as water depth, flow speed, duration, and submerged area, are analyzed. Third, based on the above-mentioned flood forecasting and flood evolution calculations, the relative membership function (VFS) is determined via the set pair analysis method (SPA), and the variable fuzzy set model (SPAVFS) is used for flood risk assessment. Finally, through the study of flow forecasting at Zhouqu hydrological station, it is found that the accuracy of the forecast result of the built model is best compared with LSTM and XAJ model, the mean relative error is only 7.6%, and the certainty coefficient can reach 0.96, which surpass the baselines by 20% and 7.9%.

show abstract

Section: Datasetsmentioning

confidence: 99%

A Multiple Model Approach for Flood Forecasting, Simulation, and Evaluation Coupling in Zhouqu County

Li,

Liu,

Liu

et al. 2023

Water

View full text Add to dashboard Cite

show abstract

“…Li et al [20] considered a costsensitive Bayesian network and weighted K-nearest neighbor model to predict the duration of accidents. To minimize the negative impacts brought by floods, researchers propose a hierarchical Bayesian network-based incremental model to predict floods for small rivers [21]. Further, using the biological information from the literature to develop a Bayesian network along with a messaging passing algorithm, progress can be made in the treatment of breast cancer [22].…”

Section: Bayesian Network Dynamic Inferencementioning

confidence: 99%

Dynamic Knowledge Inference Based on Bayesian Network Learning

Wang

Jaharadak

Xiao

2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

On the basis of studying datasets of students' course scores, we constructed a Bayesian network and undertook probabilistic inference analysis. We selected six requisite courses in computer science as Bayesian network nodes. We determined the order of the nodes based on expert knowledge. Using 356 datasets, the K2 algorithm learned the Bayesian network structure. Then, we used maximum a posteriori probability estimation to learn the parameters. After constructing the Bayesian network, we used the message-passing algorithm to predict and infer the results. Finally, the results of dynamic knowledge inference were presented through a detailed inference process. In the absence of any evidence node information, the probability of passing other courses was calculated. A mathematics course (a basic professional course) was chosen as the evidence node to dynamically infer the probability of passing other courses. Over time, the probability of passing other courses greatly improved, and the inference results were consistent with the actual values and can thus be visualized and applied to an actual school management system.

show abstract

The Use of Bayesian Acyclic Network to Assess the Impact of Digital Technology Attributes on Sustainability Pillars

Ginters

Basdogan

2021

2021 Fifth World Conference on Smart Trends in Systems Security and Sustainability (WorldS4)

View full text Add to dashboard Cite

Hierarchical Bayesian Network Based Incremental Model for Flood Prediction

Cited by 3 publications

References 15 publications

A Multiple Model Approach for Flood Forecasting, Simulation, and Evaluation Coupling in Zhouqu County

A Multiple Model Approach for Flood Forecasting, Simulation, and Evaluation Coupling in Zhouqu County

Dynamic Knowledge Inference Based on Bayesian Network Learning

The Use of Bayesian Acyclic Network to Assess the Impact of Digital Technology Attributes on Sustainability Pillars

Contact Info

Product

Resources

About