A BiLSTM-Based Hybrid Ensemble Approach for Forecasting Suspended Sediment Concentrations: Application to the Upper Yellow River

Created by W.Langdon from gp-bibliography.bib Revision:1.8620

@Article{fan:2025:Land,

• author = "Jinsheng Fan and Renzhi Li and Mingmeng Zhao and Xishan Pan",
• title = "A {BiLSTM-Based} Hybrid Ensemble Approach for Forecasting Suspended Sediment Concentrations: Application to the Upper Yellow River",
• journal = "Land",
• year = "2025",
• volume = "14",
• number = "6",
• pages = "Article No. 1199",
• keywords = "genetic algorithms, genetic programming",
• ISSN = "2073-445X",
• URL = "https://www.mdpi.com/2073-445X/14/6/1199",
• DOI = "10.3390/land14061199",
• abstract = "Accurately predicting suspended sediment concentrations (SSC) is vital for effective reservoir planning, water resource optimisation, and ecological restoration. This study proposes a hybrid ensemble model--VMD-MGGP-NGO-BiLSTM-NGO--which integrates Variational Mode Decomposition (VMD) for signal decomposition, Multi-Gene Genetic Programming (MGGP) for feature filtering, and a double-optimised NGO-BiLSTM-NGO (Northern Goshawk Optimisation) structure for enhanced predictive learning. The model was trained and validated using daily discharge and SSC data from the Tangnaihai Hydrological Station on the upper Yellow River. The main findings are as follows: (1) The proposed model achieved an NSC improvement of 19.93percent over the Extreme Gradient Boosting (XGBoost) and 15.26percent over the Convolutional Neural Network--Long Short-Term Memory network (CNN-LSTM). (2) Compared to GWO- and PSO-based BiLSTM ensembles, the NGO-optimised VMD-MGGP-NGO- BiLSTM-NGO model achieved superior accuracy and robustness, with an average testing-phase NSC of 0.964, outperforming the Grey Wolf Optimisation (GWO) and Particle Swarm Optimisation (PSO) counterparts. (3) On testing data, the model attained an NSC of 0.9708, indicating strong generalisation across time. Overall, the VMD-MGGP-NGO-BiLSTM-NGO model demonstrates outstanding predictive capacity and structural synergy, serving as a reliable reference for future research on SSC forecasting and environmental modelling.",
• notes = "also known as \cite{land14061199}",

}

Genetic Programming entries for Jinsheng Fan Renzhi Li Mingmeng Zhao Xishan Pan

Citations