Application of Rainfall-Runoff Simulation Based on the NARX Dynamic Neural Network Model

Shao, Yuehong; Jing, Zhao; Xu, Jinchao; Fu, Aolin; Li, Min

doi:10.3390/w14132082

Cited by 9 publications

(4 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With two input variables, one hidden layer, ten hidden neurons, and five-time delay based on experience, the NARX model's ideal architecture was established. The minimum of MSE was 4.12 × 10 −2 [36]. In our study, the optimal combination of the time delay and the hidden neurons number was obtained by the improved algorithm and the minimum of MSE was 1.975 × 10 −4 .…”

Section: Discussionmentioning

confidence: 62%

“…It is worth noting that few GRA-NARX models are available for predicting water levels in front of pumping stations. Moreover, in previous NARX models, the time delay and the hidden neurons number are selected based on experience [35,36], and there is a need to determine the optimal combination of the time delay and the hidden neurons number to obtain the most accurate prediction. In addition, Levenberg-Marquardt (LM) is the most frequently used training algorithm in current NARX neural networks and other algorithms are seldom used.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel GRA-NARX Model for Water Level Prediction of Pumping Stations

Liu

Lei

et al. 2022

Water

View full text Add to dashboard Cite

It is necessary but difficult to accurately predict the water levels in front of the pumping stations of an open-channel water transfer project because of the complex interactions among hydraulic structures. In this study, a novel GRA-NARX (gray relation analysis—nonlinear auto-regressive exogenous) model is proposed based on a gray relation analysis (GRA) and nonlinear auto-regressive exogenous (NARX) neural network for 2 h ahead for the prediction of water levels in front of pumping stations, in which an improved algorithm of the NARX neural network is used to obtain the optimal combination of the time delay and the hidden neurons number, and GRA is used to reduce the prediction complexity and improve the prediction accuracy by filtering input factors. Then, the sensitivity to changes of the training algorithm is analyzed, and the prediction performance is compared with that of the NARX and GRA-BP (gray relation analysis back-propagation) models. A case study is performed in the Tundian pumping station of the Miyun project, China, to demonstrate the reliability and accuracy of the proposed model. It is revealed that the GRA-NARX-BR (gray relation analysis—nonlinear auto-regressive exogenous—Bayesian regularization) model has higher accuracy than the model based only on a NARX neural network and the GRA-BP model with a correlation coefficient (R) of 0.9856 and a mean absolute error (MAE) of 0.00984 m. The proposed model is effective in predicting the water levels in front of the pumping stations of a complex open-channel water transfer project.

show abstract

Section: Discussionmentioning

confidence: 62%

Section: Introductionmentioning

confidence: 99%

A Novel GRA-NARX Model for Water Level Prediction of Pumping Stations

Liu

Lei

et al. 2022

Water

View full text Add to dashboard Cite

show abstract

“…[67], [69] [86], [131], [148], [149] [47] [38] [39], [40] [83], [84], [85], [101], [105], [134], [136], [137], [147], [150] [42], [43], [44] [75] [132] using theoretical models (namely, Green-Ampt model, see later) during storm events generating runoff. Comparing the first and second plots, we can observe that the hyetographs for storm events that result in runoff are typically skewed to the right, denoting a tendency for the storm to increase in intensity after some time from the start of rainfall.…”

Section: A Storm Eventsmentioning

confidence: 99%

Sensor Networks, Data Processing, and Inference: The Hydrology Challenge

Zanella,

Zubelzu,

Bennis

2023

IEEE Access

View full text Add to dashboard Cite

In the last years, many European countries have experienced the effects of climate change, in the form of a scarcity of drinking water resources, prolonged periods of drought, and extremely heavy rainfall, with unprecedented dramatic environmental, economic, and social costs. Therefore, understanding, modeling, and predicting the movement and distribution of water on Earth, and effectively managing water resources are problems of paramount importance. In this article, we discuss the fundamental role that sensing technologies, data processing algorithms, and inference based on machine learning techniques can have in modern hydrology and the many challenges that still need to be addressed to improve the accuracy and reduce the complexity of current hydrology models. More specifically, we overview the main solutions proposed in the literature to monitor, analyze and predict hydrological processes, and present a selection of results obtained from empirical data sets to ground the main concepts and substantiate the dissertation. Finally, we conclude our article by discussing open problems and possible avenues for future research.

show abstract

“…The remaining components were subjected to auto and cross-correlation algorithms to detect substantial time delays [5]. The NARX model is used in simulating rainfall-runoff patterns within the Linyi watershed [6]. In a study conducted by researchers in [7], the combination of Principal Component Analysis (PCA), Self-Organizing Map (SOM) and NARX known as PCA-SOM-NARX were used.…”

Section: Introductionmentioning

confidence: 99%

Rainfall-Runoff Modeling Using Artificial Neural Network for Batu Pahat River Basin

Zulkiflee,

Mohd Safar,

Kamaludin

et al. 2024

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

This research delves into the effectiveness of Artificial Neural Networks with Multilayer Perceptron (ANN-MLP) and Nonlinear AutoRegressive with eXogenous inputs (NARX) models in predicting short-term rainfall-runoff patterns in the Batu Pahat River Basin. This study aims to predict river water levels using historical rainfall and river level data for future intervals of 1, 3, and 6 hours. Data preprocessing techniques, including the management of missing values, identification of outliers, and reduction of noise, were applied to enhance the accuracy and dependability of the models. This study assessed the performance of the models for ANN-MLP and NARX by comparing their effectiveness across various forecast timeframes and evaluating their performance in different scenarios. The findings of the study revealed that the ANN-MLP model showed robust performance in short-term prediction. On the contrary, the NARX model exhibited higher accuracy, particularly in capturing intricate temporal relationships and external impacts on river behavior. The ANN-MLP produces 99% accuracy for 1-hour prediction, and NARX yields 98% accuracy with 0.3245 Root Mean Squared Error and 0.1967 Mean Absolute Error. This study makes a valuable contribution to hydrological forecasting by presenting a rigorous and precise modeling methodology.

show abstract

Application of Rainfall-Runoff Simulation Based on the NARX Dynamic Neural Network Model

Cited by 9 publications

References 52 publications

A Novel GRA-NARX Model for Water Level Prediction of Pumping Stations

A Novel GRA-NARX Model for Water Level Prediction of Pumping Stations

Sensor Networks, Data Processing, and Inference: The Hydrology Challenge

Rainfall-Runoff Modeling Using Artificial Neural Network for Batu Pahat River Basin

Contact Info

Product

Resources

About