12/29/2023 0 Comments Vmd model![]() 13 used the sparrow search algorithm (SSA) to optimize artificial neural networks (ANN model), showcasing the advantages of simple implementation, high search accuracy, fast convergence speed, stability, and robustness. Seo 11 and He 12 developed a combined runoff prediction model based on the VMD algorithm, demonstrating improved prediction accuracy after data decomposition and reconstruction. However, when the LSTM model learns time series, it faces challenges such as a poor early feature memory effect, leading to the loss of features in the initial learned part, and difficulties in fully capturing the entire time series features 10.Īs research progresses, there is an increasing demand for higher accuracy in runoff prediction. The Long Short Term Memory (LSTM) neural network model has been widely employed in runoff prediction due to its nonlinear prediction capability, faster convergence speed, and long-term memory effect. Fan Hongxiang and others developed a meteorological runoff model for the Poyang Lake basin based on the Long short-term memory neural network, effectively simulating the runoff process, capturing extreme runoff values, and reflecting short-term fluctuations. 9 utilized LSSVM and CEEMDAN to predict monthly runoff at Changshui hydrological station. The LSTM model demonstrated strong adaptability to various prediction indicators. Roy 8 used the LSTM model to predict ET0 in multiple watersheds with daily and multi-step forward predictions. 7 proposed a prediction model that combines empirical mode decomposition and Metropolis Hastings sampling Bayesian model for hydrological prediction. 6 combined quantum behavioural particle swarm optimization algorithms with variational modal decomposition and SVM to build a monthly runoff prediction model. Both domestic and foreign researchers have conducted extensive studies to improve the accuracy of prediction models, resulting in fruitful results. The pursuit of a runoff prediction model with high accuracy and applicability has been a topic of constant concern in hydrological forecasting. ![]() These models involve various optimization algorithms such as Chaos Optimization Algorithm 1, bald eagle search optimization algorithm 2, Particle Swarm Optimization (PSO) 3, and artificial neural network models 4, 5, which have deepened their intersectionality with hydrology. With the rapid advancement of artificial intelligence technology, numerous deep learning algorithms have emerged, and comprehensive forecasting models based on intelligent methods and numerical weather prediction have been proposed. They are crucial for the efficient utilization of water resources, flood control, and disaster reduction. Runoff simulation and prediction play a vital role in water resource management, regulation, and rational planning. This model holds promise for the effective prediction of monthly runoff in the lower Yellow River. In conclusion, the proposed VMD-SSA-BiLSTM model, utilizing the sparrow search algorithm and bidirectional long and short-term memory neural network, enhances the smoothness of the monthly runoff series and improves the accuracy of point predictions. The Root-mean-square deviation of VMD-SSA-BiLSTM model is 30.6601, which is 242.5124 and 39.9835 lower compared to the BiLSTM model and the VMD-BiLSTM model respectively the mean absolute percentage error is 5.6832%, which is 35.5937% and 6.3856% lower compared to the other two models, respectively the mean absolute error was 19.8992, which decreased by 136.7288 and 25.7274 respectively the square of the correlation coefficient ( R 2) is 0.93775, which increases by 0.53059 and 0.14739 respectively the Nash–Sutcliffe efficiency coefficient was 0.9886, which increased by 0.4994 and 0.1122 respectively. The results demonstrate that the VMD-SSA-BiLSTM model outperforms both the BiLSTM model and the VMD-BiLSTM model in terms of prediction accuracy during both the training and validation periods. The proposed model was applied to predict monthly runoff at GaoCun hydrological station in the lower Yellow River. This study proposes a VMD-SSA-BiLSTM coupled model for monthly runoff volume prediction, which combines the advantages of Variational Modal Decomposition (VMD) for signal decomposition and preprocessing, Sparrow Search Algorithm (SSA) for BiLSTM model parameter optimization, and Bi-directional Long and Short-Term Memory Neural Network (BiLSTM) for exploiting the bi-directional linkage and advanced characteristics of the runoff process. The accurate prediction of monthly runoff in the lower reaches of the Yellow River is crucial for the rational utilization of regional water resources, optimal allocation, and flood prevention.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |