为进一步提高径流预测精度和泛化能力,根据回归支持向量机(SVR)特性及基本原理,提出考虑不同影响因子(输入向量)的SVR集成预测模型,以云南省南盘江西桥站1961—2007年径流预测为例进行实例研究。首先,利用相关分析法选取年径流预测的若干影响因子,依次构建不同影响因子的SVR单一模型对研究实例进行预测,并构建对应的RBF模型作为对比预测模型;然后,采用加权平均和简单平均2种方法对具有较好预测精度和互补性的单一模型的预测结果进行综合集成。结果表明基于SVR的加权平均和简单平均2种集成模型径流预测的平均相对误差绝对值分别为1.27%和1.54%,最大相对误差绝对值分别为2.99%和2.74%,其精度和泛化能力均大幅优于各单一模型以及基于RBF的加权平均和简单平均集成模型,表明加权平均SVR和简单平均SVR集成模型具有较高的预测精度和泛化能力。相对而言,加权平均集成模型赋予了预测效果好的模型更大的权重,预测精度和泛化能力均优于简单平均集成模型。预测模型和方法可为相关预测研究提供参考和借鉴。
Abstract
An ensemble model involving different impact factors (input vectors) based on support vector regression (SVR) is put forward to improve runoff prediction accuracy and generalization ability. The runoff at Nanpanjiang west bridge station in Yunnan from 1961 to 2007 is taken as a case study. First, a number of impact factors for annual runoff forecast are selected to build different models for the study of a single instance of SVR, and the corresponding RBF models are built as a comparison. In subsequence, the results of single models (which are accurate and complementary) are integrated by using weighted average and simple average respectively. Results showed thatthe average relative absolute error of weighted average and simple average ensemble model based on SVR was respectively 1.27% and 1.54%, and the maximum relative absolute error is 2.99% and 2.74%. The accuracy and generalization capabilities are significantly superior to the single models as well as the weighted average and simple average ensemble model based on RBF models. The weighted average ensemble model based on SVR has better accuracy and generalization capability than simple average because it gives more weight to the models with good prediction result.
关键词
径流预测 /
集成模型 /
回归支持向量机 /
加权平均 /
简单平均
Key words
runoff forecasting /
ensemble model /
SVR /
weighted average /
simple average
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 田景文,高美娟.人工神经网络算法研究及应用[M].北京:北京理工大学出版社,2006. (TIAN Jing-wen, GAO Mei-juan. Artificial Neural Network Algorithm: Research and Application [M]. Beijing: Beijing Institute of Technology Press, 2006.(in Chinese))
[2] 田雨波.混合神经网络技术[M].北京:科学出版社,2009. (TIAN Yu-bo. Hybrid Neural Network Technology [M]. Beijing: Science Press, 2009.(in Chinese))
[3] 王 雷.支持向量机在汽轮机状态监测中的应用[M].北京:北京师范大学出版社,2012. (WANG Lei. Application of Support Vector Machine to the Monitoring of Steam Turbine[M]. Beijing: Beijing Normal University Press, 2012. (in Chinese))
[4] 张 楠,夏自强,江 红.基于多因子量化指标的支持向量机径流预测[J].水利学报,2010,41(11):1318-1323. (ZHANG Nan, XIA Zi-qiang, JIANG Hong. Prediction of Runoff Based on the Multiple Quantity Index of SVM[J]. Journal of Hydraulic Engineering, 2010, 41(11): 1318-1323. (in Chinese))
[5] 肖浩波,谷艳昌.混凝土坝安全监控最小二乘支持向量机模型[J].raybet体育在线
院报,2013,30(5):34-37. (XIAO Hao-bo, GU Yan-chang. Monitoring Model for Concrete Dam Safety Using Least Square Support Vector Machine[J]. Journal of Yangtze River Scientific Research Institute, 2013, 30(5): 34-37. (in Chinese))
[6] 李代华,崔东文. 相空间重构支持向量机在径流模拟中的应用研究[J].raybet体育在线
院报,2013,30(10):21-26. (LI Dai-hua, CUI Dong-wen. Phase Space Reconstruction of Support Vector Machine in Runoff Simulation[J]. Journal of Yangtze River Scientific Research Institute, 2013,30 (10): 21-26. (in Chinese))
[7] 李 波,刘明军,马奕仁,等.基于平均曲率模态和最小二乘支持向量机的混凝土拱坝损伤识别方法研究[J].raybet体育在线
院报,2013,30(11):113-118. (LI Bo, LIU Ming-jun, MA Yi-ren, et al. Damage Identification of Concrete Arch Dam Using Mean Curvature Mode and Least Squares Support Vector Machine [J]. Journal of Yangtze River Scientific Research Institute, 2013,30 (11): 113-118. (in Chinese))
[8] 徐 飞,徐卫亚,刘大文,等.洞室围岩变形预测的ACA-LSSVM模型及工程应用研究[J].raybet体育在线
院报,2009,26(2):32-35. (XU Fei, XU Wei-ya, LIU Da-wen, et al. ACA-LSSVM for Deformation Forecasting of Cavern Surrounding Rock and Its Application[J]. Journal of Yangtze River Scientific Research Institute, 2009,26 (2): 32-35. (in Chinese))
[9] 崔东文. 支持向量机在湖库营养状态识别中的应用研究[J].水资源保护,2013,29(4):26-30. (CUI Dong-wen. Application of Support Vector Machine to Lake and Reservoir Trophic Status Recognition[J]. Water Resource Protection, 2013,29 (4): 26-30. (in Chinese))
[10]崔东文.支持向量机在水资源类综合评价中的应用研究——以全国31个省级行政区水资源合理性配置为例[J].水资源保护,2013,29(5):20-27. (CUI Dong-wen. Support Vector Machine for Comprehensive Evaluation of Water Resources: Application to Reasonable Allocation of Water Resources in 31 Provincial-level Administrative Regions in China[J]. Water Resource Protection, 2013,29 (5): 20-27. (in Chinese))
[11]SOLLICH P, KROGH A. Learning with Ensemble: How Over-fitting Can be Useful[M]. Cambridge: MIT Press, 1996: 190-193.
[12]史 峰,王 辉,郁 磊,等. MATLAB智能算法30个案例分析[M].北京:北京航空航天大学出版社,2011. (SHI Feng, WANG Hui, YU Lei, et al. MATLAB Intelligent Algorithm: 30 Case Analysis [M]. Beijing: Beihang University Press, 2011. (in Chinese))
PDF(1041 KB)
