[1]衣学军,魏守科*,石玉好,等.基于小波非线性自回归网络的水文预测模型[J].计算机技术与发展,2021,31(03):70-77.[doi:10. 3969 / j. issn. 1673-629X. 2021. 03. 012]
　YI Xue-jun,WEI Shou-ke *,SHI Yu-hao,et al.Hydrological Series Prediction Model Based on Wavelet Nonlinear Autoregressive Network[J].,2021,31(03):70-77.[doi:10. 3969 / j. issn. 1673-629X. 2021. 03. 012]
点击复制

基于小波非线性自回归网络的水文预测模型()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年03期
页码:
70-77
栏目:
大数据分析与挖掘
出版日期:
2021-03-10

文章信息/Info

Title:
Hydrological Series Prediction Model Based on Wavelet Nonlinear Autoregressive Network
文章编号:
1673-629X(2021)03-0070-08
作者:
衣学军1; 魏守科2; 3; 4*; 石玉好1; 付常璐1; 邢昱臻1; 闫 杰1; 赵金东2
1. 烟台市水文局,山东 烟台 264000;
2. 烟台大学 计算机与控制工程学院,山东 烟台 264005;
3. 山东琢瑜清泉智能软件科技有限公司,山东 烟台 264000;
4. 北京迪普讯智能信息技术有限公司,北京 100089
Author(s):
YI Xue-jun1; WEI Shou-ke2; 3; 4 *; SHI Yu-hao1; FU Chang-lu1; XING Yu-zhen1; YAN Jie1; ZHAO Jin-dong2
1. Yantai Hydrology Bureau,Yantai 264000,China;
2. School of Computer and Controlling Engineering of Yantai University,Yantai 264005,China;
3. Jouryu Qingquan Intell. Soft. Tech. Co. ,Ltd. ,Yantai 264000,China;
4. Deepsim Intelligent Information Technology Co. ,Ltd. ,Beijing 100089,China
关键词:
水文预测; 小波变换; Daubechies; 非线性自回归网络; 贝叶斯正则化; 渭河
Keywords:
hydrological prediction;  wavelet transform;  Daubechies;  nonlinear autoregressive network;  Bayesian regularization;  Weihe River
分类号:
TP183;P333. 9;P334. 9
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 03. 012
摘要:
不同时间尺度上的水文序列预测在水资源调配和防洪减灾决策中起着重要的作用。 提出了一种基于小波分解和非线性自回归神经网络相结合的水文时间序列预测模型(WNARN)。 运用 Daubechies 5(db5)离散小波将水文序列数据分解为低频和高频子序列,作为非线性自回归神经网络模型(NARN)的输入变量,贝叶斯正则化优化算法用来泛化网络,训练模型对各子序列进行模拟预测,预测值经 db5 小波重构后得到原序列预测值。 利用渭河流域三个水文站 40 多年的月径流量序列对所提出的 WNARN 模型进行验证和向前 48 步的预测能力测试, 并与单一 NARN 模型的验证和预测结果进行对比。 结果显示在相同的网络结构下所提出的方法能够显著提高水文序列的预测精度、预测周期及对重大水文事件的预测性,具有较高的泛化能力。
Abstract:
Hydrological series prediction at different time scales plays an important role in water resources allocation, flood control and disaster reduction decisions. We propose a hydrological time series prediction model based on wavelet decomposition and nonlinear autoregressive neural network (WNARN). Daubechies 5 (db5) Disc-rete Wavelet is used to decompose hydrological series data into lowfrequency and high - frequency subseries, which are taken as the input variables of nonlinear autoregressive neural network model (NARN),and Bayes-ian regularization (BR) optimization algorithm is used to generalize the network. The NARN is trained to model and predict each of the decomposed subseries,and the predicted values of the subseries will be reconstructed through db5 wavelet and generate the predicted value of original series. The proposed model was validated and tested by 48-step ahead forecasting using over 40 years historical monthly runoff series from three hydr-ological stations in the Weihe River Basin,and the validation and testing results are compared with these of the single NARN models. The results show that under the same net structure the proposed model will signi-ficantly improve the prediction accuracy,prediction period and the ability of predicting major hydrological events with a high generalization ability.

相似文献/References:

[1]杨亚 王铮 张素兰 郭飞飞.基于小波变换的多聚焦图像融合[J].计算机技术与发展,2010,(03):56.
　YANG Ya,WANG Zheng,ZHANG Su-lan,et al.Multi - focus Image Fusion Scheme Based on Wavelet Transform[J].,2010,(03):56.
[2]刘会英 张政保 文家福 李占德.一种带纠错编码的小波域自适应盲水印算法[J].计算机技术与发展,2010,(03):140.
　LIU Hui-ying,ZHANG Zheng-bao,WEN Jia-fu,et al.A Wavelet Domain Adaptive Blind Watermarking Algorithm with Error Correcting Encoding[J].,2010,(03):140.
[3]郭航宇 景晓军 尚勇.基于小波变换和数学形态法的车牌定位方法研究[J].计算机技术与发展,2010,(05):13.
　GUO Hang-yu,JING Xiao-jun,SHANG Yong.License Plate Location Method Based on Wavelet Transform and Mathematical Morphology[J].,2010,(03):13.
[4]钱颖雪 左洪福 李耀华.小波与傅里叶变换耦合的静电监测信号去噪法[J].计算机技术与发展,2009,(07):1.
　QIAN Ying-xue,ZUO Hong-fu,LI Yao-hua.Static Monitoring Signal De- noising by Wavelet and FFT[J].,2009,(03):1.
[5]赵兵.小波变换阈值降噪在电力负荷管理终端中的应用[J].计算机技术与发展,2009,(07):206.
　ZHAO Bing.Application of Wavelet Transform Threshold Noise Reduction in Load Management Terminal[J].,2009,(03):206.
[6]张登银 薄顺荣 许扬扬.边缘检测算法改进及其在QoE测定中的应用[J].计算机技术与发展,2009,(08):49.
　ZHANG Deng-yin,BO Shun-rong,XU Yang-yang.Improved Image Edge Detection Algorithm and Its Application in QoE Measurement[J].,2009,(03):49.
[7]朱良燕 毛军军 苗强 吴涛[].合肥市降水变化趋势分形特征分析与预测[J].计算机技术与发展,2009,(09):17.
　ZHU Liang-yan,MAO Jun-jun,MIAO Qiang,et al.Analysis of Precipitation Changes Trend Fractal Features and Forecasts in Hefei[J].,2009,(03):17.
[8]王树梅 王志成 蔡健.一种基于灰度形态学的小波域边缘检测算法[J].计算机技术与发展,2009,(01):32.
　WANG Shu-mei,WANG Zhi-cheng,CAI Jian.A Novel Edge- Detection Algorithm in Wavelet Gray - Scale Morphology[J].,2009,(03):32.
[9]单立场 蔡坤宝 王永东.多分辨率分析在HRV信号分析中的应用[J].计算机技术与发展,2008,(01):250.
　SHAN Li-chang,CAI Kun-bao,WANG Yong-dong.Application of Multi Resolution Analysis to HRV Signal Analysis[J].,2008,(03):250.
[10]邢丹俊 王继成.基于提升小波的自适应阈值图像去噪[J].计算机技术与发展,2008,(02):42.
　XING Dan-jun,WPNG Ji-cheng.Adaptive Threshold Based on Lifting Wavelet Transform for Image Denoising[J].,2008,(03):42.

更新日期/Last Update: 2020-03-10