基于多模型组合方法的公平水库中长期入库径流预报  

Medium and long-term inflow runoff forecast of Gongping reservoir based on multi-model combined method

作　　者：肖三明 刘涛 XIAO Sanming;LIU Tao(Water Conservancy and Hydropower Planning and Design Institute of Shanwei,Shanwei Guangdong,516600,China;Goldwind Science&Technology Company Limited,Beijing,100176,China)

机构地区：[1]汕尾市水利水电建筑工程勘测设计室,广东汕尾516600 [2]金风科技股份有限公司,中国北京100176

出　　处：《江西水利科技》2023年第5期352-357,共6页Jiangxi Hydraulic Science & Technology

摘　　要：准确可靠的水库中长期预报结果对于指导受水区水资源优化配置等具有重要意义。本文首先选取SARIMA模型、SVM模型、XGBoost模型与RF模型分别构建公平水库月入库径流预报方案,以气象因子的物理机制为基础,在成因分析与随机森林重要性排序的基础上筛选关键预报因子并输入至4个单一模型中。然后在对比分析各模型优劣的基础上,以线性与非线性组合2种方式构建组合预报方案。结果表明:RF模型在4个单一模型中的模拟结果表现最优,SARIMA模型的模拟精度随着入库径流量的增加而增加;组合预报模型较任一单一模型的模拟结果均更好,基于神经网络的非线性组合方式能够有效提高验证期的模拟精度,增加模型的泛化能力。Accurate and reliable medium and long-term forecast results of reservoirs are of great significance for guiding the optimal allocation of water resources in the intake area.In this paper,the SARIMA model,SVM model,XGBoost model and RF model were first selected to construct the monthly runoff forecasting scheme of the reservoir.Based on the physical mechanism of meteorological factors,the key predictors were screened on the basis of the cause analysis and random forest importance ranking and were input into four single models.Then,on the basis of comparative analysis of the advantages and disadvantages of each model,a combined forecasting scheme is constructed in two ways of linear and nonlinear combination.The results show that the simulation results of the RF model are the best among the four single models,and the simulation accuracy of the SARIMA model increases with the increase of the inflow runoff;the combined forecast model is better than any single model.The nonlinear combination of neural networks can effectively improve the simulation accuracy of the verification period and increase the generalization ability of the model.

关 键 词：入库径流 中长期预报 组合预报 公平水库 线性加权 人工神经网络 

分 类 号：P338.2[天文地球—水文科学]