On-line multistep-ahead inundation depth forecasts by recurrent NARX networks

Shen, Hung-Yu; Chang, Li-Chiu

doi:10.5194/hessd-9-11999-2012

Cited by 6 publications

(5 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The objective of this work is to develop a multistep flood forecast method for urban areas at a fine spatial resolution of 4 m by 4 m. Unlike Lin et al [20], in this study, an ANN-based framework is proposed for performing multistep forecasts for 1-5 h. To the author's knowledge, only the works of Chang et al [2] and Shen and Chang [21] were able to produce multistep flood forecasting maps. The novelty herein is the forecast at a finer resolution of 4 m × 4 m, suitable for urban flood forecast.…”

Section: Introductionmentioning

confidence: 99%

Multistep Flood Inundation Forecasts with Resilient Backpropagation Neural Networks: Kulmbach Case Study

Lin

Leandro

Gerber

et al. 2020

Water

View full text Add to dashboard Cite

Flooding, a significant natural disaster, attracts worldwide attention because of its high impact on communities and individuals and increasing trend due to climate change. A flood forecast system can minimize the impacts by predicting the flood hazard before it occurs. Artificial neural networks (ANN) could efficiently process large amounts of data and find relations that enable faster flood predictions. The aim of this study is to perform multistep forecasts for 1–5 h after the flooding event has been triggered by a forecast threshold value. In this work, an ANN developed for the real-time forecast of flood inundation with a high spatial resolution (4 m × 4 m) is extended to allow for multiple forecasts. After trained with 120 synthetic flood events, the ANN was first tested with 60 synthetic events for verifying the forecast performance for 3 h, 6 h, 9 h and 12 h lead time. The model produces good results, as shown by more than 81% of all grids having an RMSE below 0.3 m. The ANN is then applied to the three historical flood events to test the multistep inundation forecast. For the historical flood events, the results show that the ANN outputs have a good forecast accuracy of the water depths for (at least) the 3 h forecast with over 70% accuracy (RMSE within 0.3 m), and a moderate accuracy for the subsequent forecasts with (at least) 60% accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Multistep Flood Inundation Forecasts with Resilient Backpropagation Neural Networks: Kulmbach Case Study

Lin

Leandro

Gerber

et al. 2020

Water

View full text Add to dashboard Cite

show abstract

“…Root mean squared error (RMSE) is another way of evaluating the representation performance which is used extensively in the literature [56,66,67] . Shen et al [53] evaluated the performance of a multistep prediction with NARX network using RMSE [53]. RMSE is also employed to evaluate forecasting capability in [68].…”

Section: Performance Evaluation Uncertainty Management and Predictiomentioning

confidence: 99%

“…Diaconescu [52] tested the performance of NARX networks in prediction of different time series. Online multiple step ahead forecasting using NARX was implemented in [53]. NARX neural network and Elman network are used to predict storm time in [54].…”

Section: Remarkmentioning

confidence: 99%

Dynamic neural networks for gas turbine engine degradation prediction, health monitoring and prognosis

Kiakojoori

Khorasani

2015

Neural Comput & Applic

View full text Add to dashboard Cite

In this paper, the problem of health monitoring and prognosis of aircraft gas turbine engines is considered by using computationally intelligent methodologies. Two different dynamic neural networks, namely the nonlinear autoregressive with exogenous input neural networks and the Elman neural networks, are developed and designed for this purpose. The proposed dynamic neural networks are designed to capture the dynamics of two main degradations in the gas turbine engine, namely the compressor fouling and the turbine erosion. The health status and condition of the engine in terms of the turbine output temperature (TT) are then predicted subject to occurrence of these deteriorations. Various scenarios consisting of fouling and erosion separately as well as combined are considered. For each scenario, several neural networks are trained and their performance in predicting multiple flights ahead TTs is evaluated. Finally, the most suitable neural networks for achieving the best prediction are selected by using the normalized Bayesian information criterion model selection. Simulation results presented demonstrate and illustrate the effective performance of our proposed neural networkbased prediction and prognosis strategies.

show abstract

“…[13] 2. Unsupervised Learning: In this method, the main features and patterns are discovered among the data entered in the form of specific categories [18] 3. Learning by reconsolidation: In this method, learning is done through the rule of trial and error, this process of learning is a combination of supervisory learning and non-supervisory learning.…”

Section: Learning Algorithms (Training) In a Neural Networkmentioning

confidence: 99%

Optimization of Hybridization of Artificial Neuron with Chaotic Genetic Algorithm in Prediction Process/With the application

Thalabi

Heydari

Tavakoli

2023

Preprint

View full text Add to dashboard Cite

Interest in the subject of prediction has increased in recent years and modern and advanced methods have emerged, including neural network models, chaotic algorithms, hybrid algorithms, and others. All of these methods are able to learn and self-adapt to any model, and do not need assumptions for the nature of the time series. Taking more than one method may lead to an increase in the accuracy of future estimates, so a neural network and chaotic genetic algorithms are used, so a model combines the strengths of two techniques to develop a hybrid CGANN model to obtain more accurate prediction results and reduce prediction errors. The aim of this study is to shed light on some of the statistical methods used in predicting the future demand for electric power in the southern region, as well as pointing to the most accurate methods in predicting the future of energy. The annual electrical energy consumption data for the southern region was used to make a comparison through practical application and it was found that the three methods are very high accuracy and suitable for use in the prediction process, but the most accurate models are the hybrid algorithm consisting of neural networks and the chaotic genetic algorithm CGANN that gives better and more results efficient, and thus was used to predict the electrical load of the southern region up to 2032.

show abstract

On-line multistep-ahead inundation depth forecasts by recurrent NARX networks

Cited by 6 publications

References 35 publications

Multistep Flood Inundation Forecasts with Resilient Backpropagation Neural Networks: Kulmbach Case Study

Multistep Flood Inundation Forecasts with Resilient Backpropagation Neural Networks: Kulmbach Case Study

Dynamic neural networks for gas turbine engine degradation prediction, health monitoring and prognosis

Optimization of Hybridization of Artificial Neuron with Chaotic Genetic Algorithm in Prediction Process/With the application

Contact Info

Product

Resources

About