摘要
径流序列的非线性和非平稳特性使得高精度的径流预报存在困难。以组合EEMD和粒子群算法(PSO)优化的GRNN模型形成EEMD-PSO-GRNN耦合模型,预测时通过将径流序列分解为确定成分与随机成分并通过PSO优化的GRNN模型分别进行预测,预测值的加和构成径流最终预测结果。EEMD-PSO-GRNN耦合模型应用到元江中上游,并与其他模型进行比较,结果表明:EEMD-PSO-GRNN耦合模型具有更高的预测精度,对径流的总体趋势预测效果良好,但在随机成分的模拟上有待进一步完善。EEMD-PSO-GRNN耦合模型优于BP、GRNN、EEMD-BP、EEMD-GRNN模型,能有效提升径流预测的精度,可为流域中长期径流预报及水资源优化调度等提供支撑。
The non-linear and non-stationary characteristics of runoff series make it difficult to forecast runoff with high accuracy.This paper formed the EEMD-PSO-GRNN coupled model by combining the EEMD and GRNN model for particle swarm algorithm(PSO)optimization.Then,the runoff series was decomposed into deterministic and stochastic components and predicted separately by the GRNN model optimized by PSO.The sum of the predicted values constitutes the final predicted value of runoff.The EEMD-PSO-GRNN coupling model was applied to the middle and upper reaches of Yuanjiang River and compared with the prediction effects of other models.The results show that the EEMD-PSO-GRNN coupled model has a higher prediction accuracy and good effect on the overall trend of runoff,but the stochastic components simulation needs to be further improved.The EEMDPSO-GRNN coupled model performances better than BP,GRNN and EEMD-BP and EEMD-GRNN models,and can effectively improve the accuracy of runoff prediction and provide support for medium and long-term runoff forecasting and water resources optimization in the basin.
作者
郑鑫
陈俊旭
胡智文
张帆
张继辉
ZHENG Xin;CHEN Junxu;HU Zhiwen;ZHANG Fan;ZHANG Jihui(School of Earth Science,Yunnan University,Kunming 650091,China;International Joint Research Center for Karstology,Yunnan University,Kunming 650091,China)
出处
《水文》
CSCD
北大核心
2023年第4期96-103,共8页
Journal of China Hydrology
基金
云南省基础研究计划项目(2019FB145)
国家自然科学基金资助项目(42161006,41701039)
云南省教育厅科学研究基金项目(2020Y0035)。
作者简介
郑鑫(1996-),女,山西临汾人,硕士,主要研究方向为水文水资源。E-mail:zhengxin4817@126.com;通信作者:陈俊旭(1984-),男,云南宣威人,博士,副教授,主要研究方向为水土资源过程模拟。E-mail:chenjunxu@ynu.edu.cn。
