A Hybrid Model for Real-Time Probabilistic Flood Forecasting Using Elman Neural Network with Heterogeneity of Error Distributions

Wan, Xinyu; Yang, Qun; Jiang, Peng; Zhong, Ping‐an

doi:10.1007/s11269-019-02351-3

Cited by 30 publications

(10 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the research of using Recurrent Neural Networks for reservoir water level prediction, most existing studies have focused on meteorological data (precipitation), daily water level data, and reservoir operational data (flow) (Lv et al 2020;Wan et al 2019). The study of reservoir water level prediction is a complex problem, as the change in reservoir water levels is influenced by factors such as rainfall, evaporation, infiltration, and various aspects of reservoir operations.…”

Section: Discussionmentioning

confidence: 99%

Forecasting of Reservoir Water Level by Remote Sensing and Deep Learning

Jin,

Liu,

Huang

2024

Preprint

View full text Add to dashboard Cite

Accurate reservoir water level prediction is crucial for the safe operation of reservoirs and the utilization of their functions. Traditional physical-based water level forecasting methods rely heavily on auxiliary data, such as precipitation and reservoir outflow. However, obtaining timely and reliable data on reservoir discharge flow can be expensive and impractical due to limitations in infrastructure or data accessibility. To address this issue, the current study utilized multi-source remote sensing data to extract a time series of reservoir storage volume. A technical framework for predicting water levels using deep learning models and remote sensing technology was proposed. To validate the effectiveness of this method, we compared the predictive accuracy of reservoir water levels among 16 different machine learning input scenarios. The results indicate that the model incorporating water level, rainfall, water surface area, and daily changes in reservoir storage volume as input data performed the best. Compared to the input data that did not consider water surface area and daily changes in reservoir storage, it demonstrated higher accuracy, with an increase in R2 value by 1.13%, RMSE increased by 52.17%, and MAE increased by 63.80%. The framework proposed in this study offers a reliable method for predicting reservoir water levels in the absence of operational data for reservoirs.

show abstract

Section: Discussionmentioning

confidence: 99%

Forecasting of Reservoir Water Level by Remote Sensing and Deep Learning

Jin,

Liu,

Huang

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Based on a Neural Network Machine learning is gaining increasing attention in flood forecasting. However, most of these studies focus on time series predictions based on specific sensors, such as river water level and flow measured by hydrological stations and fixed-point water depth predictions at urban water monitoring stations (Zheng et al 2014;Bowes et al 2019;Wan et al 2019). There are very few temporal and spatial predictions of floods available.…”

Section: Prediction Of Spatial Multipoint Water Accumulationmentioning

confidence: 99%

A Rapid Prediction Model of Urban Flood Inundation in a High-Risk Area Coupling Machine Learning and Numerical Simulation Approaches

Yan

Feng

et al. 2021

Int J Disaster Risk Sci

View full text Add to dashboard Cite

Climate change has led to increasing frequency of sudden extreme heavy rainfall events in cities, resulting in great disaster losses. Therefore, in emergency management, we need to be timely in predicting urban floods. Although the existing machine learning models can quickly predict the depth of stagnant water, these models only target single points and require large amounts of measured data, which are currently lacking. Although numerical models can accurately simulate and predict such events, it takes a long time to perform the associated calculations, especially two-dimensional large-scale calculations, which cannot meet the needs of emergency management. Therefore, this article proposes a method of coupling neural networks and numerical models that can simulate and identify areas at high risk from urban floods and quickly predict the depth of water accumulation in these areas. Taking a drainage area in Tianjin Municipality, China, as an example, the results show that the simulation accuracy of this method is high, the Nash coefficient is 0.876, and the calculation time is 20 seconds. This method can quickly and accurately simulate the depth of water accumulation in high-risk areas in cities and provide technical support for urban flood emergency management.

show abstract

“…This study undertook the Xianghongdian Reservoir in the Huai River Basin of China as an example. Xianghongdian Reservoir [34] is located in Jinzhai County, Anhui Province. The reservoir watershed is shown in Figure 3.…”

Section: Case Study Areamentioning

confidence: 99%

Floodwater Utilization Based on Reservoir Pre-Release Strategy Considering the Worst-Case Scenario

Hua

Wan

Wang

et al. 2020

Water

Self Cite

View full text Add to dashboard Cite

Utilizing floodwater resources is important in relieving water shortages, and dynamic control of the flood limited water level (FLWL) for reservoir operation in a flood season is an effective method to achieve this objective. Based on the capacity-constrained pre-release method, this study proposed an improved dynamic control method that considered the duration of dry periods and the lead time of flood forecasts. The pre-release process was divided into two periods: water use and flood control. Taking Xianghongdian Reservoir in the Huai River Basin of China as an example, this study analyzed the statistical laws of continuous dry periods and effective flood forecast lead times and compared the effects of the negative exponential and asymptotic regression models in fitting the dry period distribution. We also calculated the floodwater volume over the FLWL in different situations and evaluated the flood control risks in a worst-case scenario. Statistical law of the dry period duration showed obvious negative index distribution characteristics; the relationship between increased water storage, dry period, and lead time can provide support for the operation decisions of the reservoir. The method did not increase the flood control risk under worst-case scenarios, and it can be used to effectively utilize reservoir floodwater resources.

show abstract

A Hybrid Model for Real-Time Probabilistic Flood Forecasting Using Elman Neural Network with Heterogeneity of Error Distributions

Cited by 30 publications

References 55 publications

Forecasting of Reservoir Water Level by Remote Sensing and Deep Learning

Forecasting of Reservoir Water Level by Remote Sensing and Deep Learning

A Rapid Prediction Model of Urban Flood Inundation in a High-Risk Area Coupling Machine Learning and Numerical Simulation Approaches

Floodwater Utilization Based on Reservoir Pre-Release Strategy Considering the Worst-Case Scenario

Contact Info

Product

Resources

About