[1]郭皓,邢贞相,付强,等.基于密度参数K-均值算法的RBF网络及其在降水量预测中的应用[J].水土保持研究,2014,21(06):299-303.
　GUO Hao,XING Zhen-xiang,FU Qiang,et al.RBF Neural Network of K-Means Algorithm Based on Density Parameter and the Application to the Rainfall Forecasting[J].Research of Soil and Water Conservation,2014,21(06):299-303.
点击复制

基于密度参数K-均值算法的RBF网络及其在降水量预测中的应用

《水土保持研究》[ISSN:1005-3409/CN:61-1272/P] 卷: 21 期数: 2014年06期 页码: 299-303 栏目: 出版日期: 2014-12-28
Title:
RBF Neural Network of K-Means Algorithm Based on Density Parameter and the Application to the Rainfall Forecasting
作者:
郭皓1, 邢贞相1,2,3, 付强1,2,3, 李晶1
1. 东北农业大学 水利与建筑学院, 哈尔滨 150030;
2. 黑龙江省粮食产能提升协同创新中心, 哈尔滨 150030;
3. 黑龙江省高校节水农业重点实验室, 哈尔滨 150030
Author(s):
GUO Hao1, XING Zhen-xiang1,2,3, FU Qiang1,2,3, LI Jing1
1. College of Water Conservancy & Civil Engineering, Northeast Agricultural University, Harbin 150030, China;
2. Collaborative Innovation Center of Grain Production Capacity Improvement in Heilongjiang Province, Harbin 150030, China;
3. Key Lab of Water-Saving Agriculture of Heilongjiang University, Harbin 150030, China
关键词:
水文学; 降水量预测; 径向基函数神经网络; 密度参数; K-均值
Keywords:
hydrology; rainfall forecasting; radial basis function neural network; density parameter; K-means
分类号:
P338
摘要:
径向基函数（Radial Basis Funtion，简称RBF）神经网络是一种收敛速度快、逼近能力强的前馈型神经网络。为提高网络的训练速度，采用基于密度参数的K-均值算法，消除传统K-均值算法对初始聚类中心的敏感性，构建了基于K-均值算法的RBF降水预报模型，并应用于挠力河流域的友谊农场汛期月降水量预报中，以检验所建模型的有效性。结果表明，与标准的K-均值算法RBF网络模型和BP（Back Propagation）网络模型相比，所构建的RBF降水预报模型对2008年，2009年，2010年各年间汛期（6—9月）降水量的预测平均相对误差为9.270 7％；确定性系数为0.96。预报精度均有所提高，且满足水文预报要求。
Abstract:
The radial basis function (RBF) neural network is a feed-forward artificial neural network with high convergence speed and strong approximation capability. In order to improve the training rate of the RBF, a K-means algorithm based on density parameter was introduced to determine clustering center, which could reduce the sensitivity of traditional K-means algorithm for initial clustering centers. A rainfall forecasting model of RBF based on K-means algorithm was built, which was applied to forecasting monthly rainfall over the Youyi Farm in Naolihe catchment during the flood season, aiming to test the effectiveness of this model. The case study showed that the mean relative error of rainfall forecasting in flood season (from June to September) of the year 2008, 2009 and 2010 was 9.270 7%, and the deterministic coefficient was 0.96. It demonstrated a higher forecasting accuracy compared to a RBF model based on a standard K-means algorithm and BP (Back Propagation) model, and the rainfall forecasting results met the requirements of hydrologic prediction.

参考文献/References:

[1] 常青,赵晓莉.时间序列模型在降水量预测中的应用研究[J].计算机仿真,2011,28(7):204-206.
[2] 唐亚松,张鑫,蔡焕杰,等.一种基于回归分析与时序分析的降水预报模型[J].水土保持通报,2009,29(1).88-92.
[3] 李才媛,顾永刚.灰色预测模型在长江上游流域面雨量预报中的应用[J].气象科技,2004,31(4):223-225.
[4] 钱莉,杨晓玲,殷玉春,等.最优子集回归在武威市降水预报中的应用[J].干旱区研究,2009,26(6):895-900.
[5] 孙才志,林学钰.降水预测的模糊权马尔可夫模型及应用[J].系统工程学报,2003,18(4):294-299.
[6] 封毅,武博强,崔灵周.基于BP神经网络的台风降雨量预测研究[J].水土保持研究,2012,19(3):289-293.
[7] 葛彩莲,蔡焕杰,王健,等.基于BP神经网络的降雨量预测研究[J].节水灌溉,2010(11):7-10.
[8] 吴有训,王周青,汪文烈,等.遗传算法优化BP网络的汛期降水预测模型[J].安徽农业大学学报,2013,40(2):299-303.
[9] 卢文喜,杨磊磊,杨忠平,等.逐步回归时间序列和RBF-ANN在降水预测中的应用[J].重庆大学学报:自然科学版,2012,35(11):131-135.
[10] 陈玉红.RBF网络在时间序列预测中的应用研究[D].哈尔滨:哈尔滨工程大学,2009.
[11] 伊燕平,卢文喜,张耘,等.基于径向基函数神经网络的地下水数值模拟模型的替代模型研究[J].水土保持研究,2012,19(4):265-269.
[12] 张德丰.MATLAB神经网络应用设计[M].北京:机械工业出版社,2009.
[13] 靳玉萍,党婕.基于径向基神经网络改进算法优化锅炉燃烧效率[J].计算机应用,2013,33(06):1771-1779.
[14] 张建辉.K-means聚类算法研究及应用[D].武汉:武汉理工大学,2007.
[15] 胡可云,田凤占,黄厚宽.数据挖掘理论与应用[M].北京:清华大学出版社,2008.
[16] 苏美娟.径向基函数神经网络学习算法研究[D].苏州:苏州大学,2007.
[17] 王文圣,丁晶,金菊良.随机水文学[M].北京:中国水利水电出版社,2008.

相似文献/References:

[1]夏梦,马龙,吉力力·阿不都外力.玛纳斯河流域中下游平原地区水化学特征及其影响因素[J].水土保持研究,2015,22(02):136.
　XIA Meng,MA Long,JILILI·Abuduwaili.The Water Chemical Characteristics and Its Influence Factors in Middle and Lower Reaches of Manasi River Basin[J].Research of Soil and Water Conservation,2015,22(06):136.
[2]段琪彩,吴灏,王杰,等.滇中城市水源地水源涵养能力研究[J].水土保持研究,2015,22(05):312.
　DUAN Qicai,WU Hao,WANG Jie,et al.Study on the Water Conservation Capacity of Urban Catchment Areas in Central Yunnan[J].Research of Soil and Water Conservation,2015,22(06):312.
[3]徐炫清,陈裕婵,李青圃,等.五华河流域景观格局演变对径流泥沙的影响[J].水土保持研究,2018,25(01):231.
　XU Xuanqing,CHEN Yuchan,LI Qingpu,et al.Effects of Landscape Patterns on Runoff and Sediment in Wuhua River Basin[J].Research of Soil and Water Conservation,2018,25(06):231.
[4]章熙锋,申东,唐家良,等.紫色土农业小流域径流过程与氮流失尺度效应[J].水土保持研究,2018,25(02):72.
　ZHANG Xifeng,SHEN Dong,TANG Jialiang,et al.Scale Effects on Characteristics of Runoff Processes and Nitrogen Losses in a Small Agricultural Catchment in Purple Soil Region[J].Research of Soil and Water Conservation,2018,25(06):72.
[5]岳思羽,李怀恩,赵 丽.气候和土地利用变化对渭河流域水资源短缺的影响[J].水土保持研究,2021,28(05):95.
　YUE Siyu,LI Huaien,ZHAO Li.Impact of Climate and Land Use Changes on Water Scarcity in the Wei River Basin[J].Research of Soil and Water Conservation,2021,28(06):95.

备注/Memo

收稿日期:2014-04-15;改回日期:2014-05-08。
基金项目:国家自然科学资助项目（51109036；51179032）；教育部高等学校博士学科点专项科研基金（20112325120009）；水利部公益性行业科研专项经费项目（201301096）；黑龙江省级领军人才梯队后备事头人资助项目（500001）；黑龙江省博士后启动金（LBH-Q12147）
作者简介:郭皓(1990-),女,黑龙江省双城人,硕士研究生,研究方向为水文预报方法研究。E-mail:ghneau@sina.cn
通讯作者:付强(1973-),男,辽宁省锦州人,博导,教授,博士,研究方向为水资源分析与评价。E-mail:fuqiang0629@126.com

更新日期/Last Update: 1900-01-01