河流流量是水文监测和水资源管理的重要指标,流量预测对于水利建设、航运规划和水资源调度等方面具有重要的指导意义和参考价值。结合变分模态分解(VMD)处理非平稳序列的优势以及BP神经网络(BPNN)处理非线性拟合的能力,提出和构建了基于VMD-BP模型的河流流量预测方法。以长江宜昌水文站为实例,基于1998年和1999年的日水位和日流量数据,对方法模型进行了验证。结果表明:VMD-BP模型在一定程度上解决了水位和流量的多值关系,降低了数据的波动性,预测结果优于线性拟合的回归模型和BPNN模型,预测误差仅为1.61%,为河流流量预测提供了一种有效的方法。
Abstract
River flow is an important ecological indicator for monitoring hydrological issues and managing water resources. Flow forecast is also significant for providing guidance and reference for water conservancy construction, navigation planning, and water resources dispatching. In the present research, a VMD-BP (variational mode decomposition and back propagation) model of forecasting river flow is proposed and constructed by combining the advantages of VMD in dealing with non-stationary sequences and the ability of BP neural network in tackling nonlinear fitting problems. The model is verified by using daily water level and flow data in 1998 and 1999 at Yichang Hydrological Station of the Yangtze River. Results indicate the VMD-BP model solves the multi-value relations between water level and flow to some extent and mitigates the volatility of data. The predicted result is better than those of linear fitting regression model and BPNN model, and the prediction error is merely 1.61%. Therefore, the VMD-BP model can be considered as an effective method for river flow prediction.
关键词
河流流量 /
变分模态分解 /
BP神经网络 /
预测模型 /
水位-流量关系 /
宜昌水文站
Key words
river flow /
variational mode decomposition /
BP neural network /
prediction model /
stage-discharge relation /
Yichang hydrologic station
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] YE X, XU C Y, LI Y,et al. Change of Annual Extreme Water Levels and Correlation with River Discharges in the Middle-Lower Yangtze River: Characteristics and Possible Affecting Factors[J]. Chinese Geographical Science, 2017, 27(2): 325-336.
[2] 刘志雨, 侯爱中, 王秀庆. 基于分布式水文模型的中小河流洪水预报技术[J]. 水文, 2015, 35(1): 1-6.
[3] LÓPEZ-VICENTE M, PéREZ-BIELSA C, LÓPEZ-MONTERO T, et al. Runoff Simulation with Eight Different Flow Accumulation Algorithms: Recommendations Using a Spatially Distributed and Open-source Model[J]. Environmental Modelling & Software, 2014, 62: 11-21.
[4] TERZI Ö, ERGIN G. Forecasting of Monthly River Flow with Autoregressive Modeling and Data-driven Techniques[J]. Neural Computing and Applications, 2014, 25(1): 179-188.
[5] 张东莱. ARIMA模型在水位预测中的应用[J]. 南水北调与水利科技, 2016,14(2): 238-240.
[6] YASEEN Z M, EL-SHAFIE A, AFAN H A, et al. RBFNN Versus FFNN for Daily River flow Forecasting at Johor River, Malaysia[J]. Neural Computing and Applications, 2016, 27(6): 1533-1542.
[7] 代兴兰. 回归支持向量机集成模型在年径流预测中的应用[J]. 长江科学院院报, 2015, 32(4): 12-17.
[8] SEO Y, KIM S. River Stage Forecasting Using Wavelet Packet Decomposition and Data-driven Models[J]. Procedia Engineering, 2016, 154: 1225-1230.
[9] FERNANDO A K, SHAMSELDIN A Y, ABRAHART R J.Use of Gene Expression Programming for Multimodel Combination of Rainfall-Runoff Models[J]. Journal of Hydrologic Engineering, 2011, 17(9): 975-985.
[10]胡 宾, 崔广柏, 朱灵芝. BP 神经网络预测河流月径流量[J]. 浙江水利科技, 2007(2):15-16.
[11]郝建浩, 唐德善, 尹 笋, 等. 基于广义回归神经网络模型的径流预测研究[J]. 水电能源科学, 2016, 34(12): 55-58.
[12]李志新, 赖志琴, 龙云墨. 基于GA-Elman神经网络模型的年径流预测[J]. 水利水电技术, 2018, 49(8): 74-80.
[13]余开华. 小波神经网络模型在河道流量水位预测中的应用[J]. 水资源与水工程学报, 2013, 24(2):204-208.
[14]席东洁, 赵雪花, 张永波, 等. 基于经验模态分解与 Elman 神经网络的月径流预测[J]. 中国农村水利水电, 2017 (7): 112-115.
[15]DRAGOMIRETSKIY K, ZOSSO D. Variational Mode Decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
[16]LONG J, WANG X, DAI D, et al. Denoising of UHF PD Signals Based on Optimised VMD and Wavelet Transform[J]. IET Science, Measurement & Technology, 2017, 11(6): 753-760.
[17]胡 强, 郝晓燕, 雷 蕾. 基于遗传算法和BP神经网络的孤立性肺结节分类算法[J]. 计算机科学, 2016, 43(6): 37-39.
[18]ZHANG N, MA Y, ZHANG Q. Prediction of Sea Ice Evolution in Liaodong Bay Based on a Back-propagation Neural Network Model[J]. Cold Regions Science and Technology, 2018, 145: 65-75.
基金
国家自然科学基金项目(41571514);长江科学院开放研究基金项目(CKWV2018499/KY)
PDF(4181 KB)
