曹伟征,李光轩,张玉国,刘东

• 1:黑龙江省水文局
• 2:东北农业大学水利与土木工程学院

摘要(Abstract)：

针对传统区域地下水埋深预测方法精度不高问题,提出一种基于相空间重构(PSR)、粒子群算法(PSO)的极限学习机(ELM)的非线性预测模型。首先利用C-C法对地下水埋深原始时序数据进行相空间重构(PSR),然后利用PSO-ELM对地下水埋深进行预测。将模型应用于中国黑龙江省红兴隆管理局红旗岭农场地下水埋深预测,结果表明:该模型取得了较好的预测效果,后验差比值C为0.074,小误差频率p为1,相对均方误差E1为6.36%,拟合准确率E2达到92.66%,试预报效果指标E3达到95.80%;与PSR-ELM、PSR-RBF等模型相比,PSR-PSO-ELM在试预报方面可使RMSE分别降低49%和70%,使误差区间分别降低28.2%和68.6%,证明PSO能够有效改善ELM模型的预测性能;分析了气候因素和人类活动对当地地下水埋深动态变化的影响。

关键词(KeyWords)： 地下水埋深;粒子群算法;极限学习机;相空间重构;预测

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金(51579044,41071053,51479032);; 国家重点研发计划(2017YFC0406002);; 黑龙江省自然科学基金(E2017007);; 黑龙江省水利科技项目(201319,201501,201503)

作者(Author): 曹伟征,李光轩,张玉国,刘东

DOI: 10.13928/j.cnki.wrahe.2018.06.007

参考文献(References)：

• [1]刘敏,黄领梅,沈冰,等.和田绿洲地下水埋深的自然影响因素分析[J].中国生态农业学报,2009,17(1):174-177.
• [2]GINOCCHI M,CROSTA G F,ROTIROTI M,et al.Analysis and prediction of groundwater level time series with Autoregressive Linear Models[J].Rendiconti online societa geologica Italiana,2016,39(3):109-112.
• [3]YAN Q,MA C.Application of integrated ARIMA and RBF network for groundwater level forecasting[J].Environmental earth sciences,2016,75(5):1-13.
• [4]LALLAHEM S,MANIA J,HANI A,et al.On the use of neural networks to evaluate groundwater levels in fractured media[J].Journal of hydrology,2005,307(1/4):92-111.
• [5]HUANG G B,ZHU Q Y,Siew C K.Extreme learning machine:Theory and applications[J].Neurocomputing,2006,70(1-3):489-501.
• [6]XIA M,ZHANG Y,WENG L,et al.Fashion retailing forecasting based on extreme learning machine with adaptive metrics of inputs[J].Knowledge-based systems,2012,36(6):253-259.
• [7]徐龙琴,张军,李乾川,等.基于EMD和ELM的工厂化育苗水温组合预测模型[J].农业机械学报,2016,47(4):265-271.
• [8]CHEN X,DONG Z Y,MENG K,et al.Electricity price forecasting with extreme learning machine and bootstrapping[J].IEEE transactions on power systems,2012,27(4):2055-2062.
• [9]HU X,SHI Y,EBERHART R.Recent advances in particle swarm[C]//Emma Hart.Developments,applications and resources:Evolutionary computation.Portland:Congress on Evolutionary Computation,2004(1):90-97.
• [10]修春波,刘向东,张宇河.相空间重构延迟时间与嵌入维数的选择[J].北京理工大学学报,2003,23(2):219-224.
• [11]PACKARD N H,CRUTCHFIELD J P,FARMER J D,et al.Geometry from a time series[J].Physical review letters,1980,45(9):712.
• [12]KIM H S,EYKHOLT R,SALAS J D.Nonlinear dynamics,delay times,and embedding windows[J].Physica D nonlinear phenomena,1999,127(1/2):48-60.
• [13]ALBANO A M,MUENCH J,SCHWARTZ C,et al.Singular-value decomposition and the Grassberger-Procaccia algorithm[J].Phys rev a gen phys,1988,38(6):3017-3026.
• [14]FRASER A M,SWINNEY H L.Independent coordinates for strange attractors from mutual information[J].Physical review a general physics,1986,33(2):1134.
• [15]胡瑜,陈涛.基于C-C算法的混沌吸引子的相空间重构技术[J].电子测量与仪器学报,2012,26(5):425-430.
• [16]王小川,史峰,郁磊.MATLAB神经网络43个案例分析[M].北京:北京航空航天大学出版社,2013.
• [17]HUANG N E,SHEN Z,LONG S R,et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].Proceedings mathematical physical&engineering sciences,1998,454(1971):903-995.
• [18]KENNEDY J,EBERHART R.Particle swarm optimization[C]//Kenji Doya.Social adaptation of knowledge:Neural networks.Piscataway:IEEE International Conference on Neural Networks,1995:1942-1948.
• [19]HAN F,YAO H F,LING Q H.An improved evolutionary extreme learning machine based on particle swarm optimization[J].Neurocomputing,2013,116:87-93.
• [20]陈南祥.地下水动态预报模型的精度评价[J].工程勘察,1999(3):35-38.
• [21]侯建英.黑龙江省红旗岭农场水稻节水灌溉模式研究[D].北京:中国农业科学院,2014.
• [22]赵阳,丁佳俊.黑龙江省红旗岭农场湿地资源保护与利用研究[J].农场经济管理,2015(4):20-22.
• [23]WOLF A,SWIFT J B,SWINNEY H L,et al.Determining lyapunov exponents from a time series[J].Physica D nonlinear phenomena,1985,16(3):285-317.
• [24]XU C,JIA H,WANG R,et al.Groundwater Level Prediction Based on BP and RBF Neural Network[J].International journal of applied science&engineering research,2014,2(3):263-269.
• [25]WEI T.Impact of energy efficiency gains on output and energy use with Cobb-Douglas production function[J].Energy policy,2007,35(4):2023-2030.
• [26]ZHANG Q,DIAO Y,DONG J.Regional water demand prediction and analysis based on cobb-douglas model[J].Water resources management,2013,27(8):3103-3113.
• [27]刘朔,李倩茹.C-D生产函数视角下水利改革对农业增产的影响因素研究[J].水利水电技术,2014,45(11):61-65.
• [28]岳国峰,张永嘉,刘东.基于多尺度熵区域地下水资源系统复杂性测度[J].东北农业大学学报,2016,47(7):101-108.