A seasonal ARIMA model based on the gravitational search algorithm (GSA) for runoff prediction

作     者：Zhang, Xianqi Wu, Xilong Zhu, Guoyu Lu, Xiaobin Wang, Kai 

作者机构：North China Univ Water Resources & Elect Power Sch Water Conservancy Zhengzhou 450046 Peoples R China Prov & Minist Cobuilt Collaborat Innovat Ctr Yellow River Basin Water Resources Efficient Util Zhengzhou 450046 Peoples R China Henan Water Conservancy & Water Transportat Engn Zhengzhou 450046 Peoples R China Sichuan Univ Coll Water Resource & Hydropower State Key Lab Hydraul & Mt River Engn Chengdu Sichuan Peoples R China 

出 版 物：《WATER SUPPLY》 (Water Supply)

年 卷 期：2022年第22卷第8期

页      面：6959-6977页

核心收录：

学科分类：0830[工学-环境科学与工程（可授工学、理学、农学学位）] 08[工学] 083305[工学-城乡生态环境与基础设施规划] 0815[工学-水利工程] 081403[工学-市政工程] 0814[工学-土木工程] 0833[工学-城乡规划学] 

基　　金：Key Scientific Research Project of Colleges and Universities in Henan Province (CN) [17A570004] 

主　　题：ARIMA model gravitational search algorithm runoff prediction seasonal differencing Wei River 

摘      要：The prediction of river runoff is crucial for flood forecasting, agricultural irrigation and hydroelectric power generation. Coupled runoff prediction model based on the Gravitational Search Algorithm (GSA) and the Seasonal Autoregressive Integrated Moving Average (SARIMA) model is proposed to address the non-linear and seasonal features of runoff data. The GSA has a significant local optimisation capability, while the SARIMA model allows for real-time adjustment of the model using historical data and is suitable for analysing time series with seasonal variations. Consequently, the GSA-SARIMA model was developed and applied to the runoff prediction of the Xianyang section of the Wei River. The results suggest that the GSA-SARIMA model achieves a linear correlation coefficient of 0.9351, a Nash efficiency coefficient of 0.91, a mean relative error of 6.57 and a root mean square error of 0.21. All of the evaluation indicators of this model outperform the other models developed, and its application to actual runoff prediction is feasible, which creates a new path for runoff prediction.