基于GWO-ELM算法模型的水体含沙量预测

泥沙含量的演变受多种因素的影响,为了快速、准确地对水中泥沙含量进行高精度预测,为泥沙治理以及合理利用水土资源提供理论依据,提出了一种基于GWO-ELM算法模型的水体含沙量预测方法.首先,将影响泥沙含量的8种原始影响因子赋予权重,利用主成分分析(principal component analysis,PCA)法提取出4...

Prediction of water sediment concentration based on GWO-ELM algorithm model

The evolution of sediment content is affected by many factors. In order to quickly and accurately predict the sediment content in water with high precision, and to provide theoretical basis for sediment management and rational utilization of water and soil resources, a prediction method of water sediment content based on GWO-ELM algorithm model was proposed. Firstly, eight original influencing factors of sediment content were weighted, and four Principal Component factors were extracted by Principal Component Analysis (PCA) to avoid dimensional disaster. Then, the extracted factors were used as the input of the Extreme Learning Machine (ELM) algorithm model to predict the sediment content, and Grey Wolf Optimizer (GWO) was used to update the optimal parameters of the prediction model. Finally, the simulation verification is carried out based on the monitoring data of the north channel of the Changjiang Estuary. The results show that the method proposed in this paper can effectively reduce the dimensional disaster, and improve the prediction accuracy under the same number of hidden layer neurons. The predicted value has a good fitting effect with the actual value, and the prediction accuracy is high. This study shows that GWO-ELM model can be used to predict sediment content, which provides some reference experience for relevant decision-making departments.