[1]伊燕平,卢文喜,许晓鸿,等.基于RBF神经网络的土壤侵蚀预测模型研究[J].水土保持研究,2013,20(02):25-28.
　YI Yan-ping,LU Wen-xi,XU Xiao-hong,et al.Research on Soil Erosion Prediction Model Based on RBF Neural Network[J].Research of Soil and Water Conservation,2013,20(02):25-28.
点击复制

基于RBF神经网络的土壤侵蚀预测模型研究

《水土保持研究》[ISSN:1005-3409/CN:61-1272/P] 卷: 20 期数: 2013年02期 页码: 25-28 栏目: 出版日期: 2013-04-28
Title:
Research on Soil Erosion Prediction Model Based on RBF Neural Network
作者:
伊燕平1,2, 卢文喜1, 许晓鸿2, 洪德法3
1. 吉林大学 环境与资源学院, 长春 130021;
2. 吉林省水土保持科学研究院, 长春 130033;
3. 长春市城乡规划设计研究院, 长春 130021
Author(s):
YI Yan-ping1,2, LU Wen-xi1, XU Xiao-hong2, HONG De-fa3
1. College of Environment and Resources, Jilin University, Changchun 130021, China;
2. Jilin Institute of Soil and Water Conservation, Changchun 130033, China;
3. Changchun Institute of Urban Planning & Designning, Changchun 130021, China
关键词:
土壤侵蚀预测; RBF神经网络; BP神经网络; 预测模型
Keywords:
soil erosion prediction; RBF neural network; BP neural network; prediction mode
分类号:
S157
摘要:
土壤侵蚀的物理机理十分复杂，用数学方式难以描述。针对土壤侵蚀过程的模糊性、随机性、非线性等特点，将RBF神经网络的理论与方法应用到土壤侵蚀预测中。以杏木小流域为研究对象，应用RBF神经网络方法构建土壤侵蚀预测模型，以汛期降雨量、径流系数、土壤容量、有机质含量及孔隙度土壤侵蚀因子作为模型的输入层变量，输出层变量为年土壤侵蚀模数。通过模拟训练和预测，RBF神经网络取得的结果较好，能够有效地预测土壤侵蚀，且与常见的BP神经网络土壤侵蚀预测模型相比，RBF神经网络得到的预测结果精度更高。RBF神经网络模型将土壤侵蚀预测问题转化为影响因子和年侵蚀模数的非线性问题，该模型的模拟与预测为复杂的土壤侵蚀规律研究提供了新途径。
Abstract:
The physical mechanism of soil erosion is so complicated that it is difficult to be described by the mathematical mode. According to the characteristic of vagueness, randomness and nonlinear of soil erosion process, the RBF neural network theory and method are applied to soil erosion prediction. With Xingmu small watershed as the research case, the application of RBF neural network method was adopted to construct soil erosion prediction model, and flood season rainfall, runoff coefficient, soil capacity, organic matter content and porosity and so on were used as input layer variables, and yearly soil erosion modulus were used as the output layer variable. Through the simulation training and the forecast, results obtained through RBF neural network were precise, RBF neural network could be used as soil erosion prediction model, compared with the traditional BP neural network, RBF neural network could give the higher accuracy prediction results. RBF neural network model shifts soil erosion prediction problem into the impact factor and erosion modulus nonlinear problem, the model of the simulation and forecast provides a new way to complex law of soil erosion research.

参考文献/References:

[1] 张光辉.土壤侵蚀模型研究现状与展望[J].水科学进展,2002,13(3):389-396.
[2] 李发鹏,李景玉,徐宗学.东北黑土区土壤退化及水土流失研究现状[J].水土保持研究,2006,13(3):50-54.
[3] 尹怀宁,汤姿,吕芳.东北平原西部近百年来生态环境退化机制分析[J].水土保持研究,2003,10(4):190-192.
[4] Smith D D. Interpretation of soil conservation data for field use[J]. Agricultural Engineering,1941,22:173-175.
[5] Wischmeier W H, Smith D D. Predicting Rainfall-Erosion Losses from Cropland East of the Rocky Mountains[M]. USDA Agricultural Handbook,No.292,1965.
[6] Wischmeier W H, Smith D D. Predicting Rainfall-Erosion Losses[M]. USDA Handbook,No.537,1978.
[7] Nearing M A, Lane L J, Alberts E E, et al. Prediction technology for soil erosion by water: status and research needs[J]. Soil Sci. Soc. Am. J., 1990,54(6):1702-1711.
[8] Morgan R. The European Soil Erosion Model: An Update on Its Structure and Research Base[M]// Rickson R. Conserving Soil Resources: European perspectives[M].CAB International,Cambridge,1994.
[9] Rose C W, Williams J R, Sander C C,et al. A mathematical model of soil erosion and deposition processes: theory for a plane land element[J]. Soil Sci Soc Am J.,1983,47(5):991-995.
[10] 符素华,张卫国,刘宝元,等.北京山区小流域土壤侵蚀模型[J].水土保持研究,2001,8(4):114-120.
[11] 张坤,丁新新,洪伟,等.BP神经网络在降雨侵蚀力预测预报中的应用研究[J].2009,16(1):53-56.
[12] 徐鼎甲.用离散微分动态规划制订梯级水电站最优日运行方式[J].水利水电技术,1996(2):33-38.
[13] Licznar P, Nearing M A. Artificial neural networks of soil erosion and runoff prediction at the plot scale[J]. Catena,2003,51(2):89-114.
[14] 赵西宁,吴普特,冯浩,等.坡面土壤侵蚀产沙的神经网络模拟[J].土壤学报,2006,43(2):324-327.
[15] 张科利,彭文英,杨红丽.中国土壤可蚀性值及其估算[J].土壤学报,2007,44(1):7-13.
[16] 毛典辉,曾致远,王乘,等.基于支持向量机的土壤侵蚀预测模型研究[J].人民长江,2007,38(8):82-84.
[17] 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.
[18] 柴杰,江青茵,曾志凯.RBF神经网络的函数逼近能力及其算法[J].模式识别与人工智能,2005,15(3):310-316.
[19] 张淮清,俞集辉.波导本征问题分析的径向基函数方法[J].电子学报,2008,36(12):2433-2438.
[20] 朱树先,张仁杰.BP和RBF神经网络在人脸识别中的比较[J].仪器仪表学报,2007,28(2):375-379.
[21] 尹江红,叶汉民,罗明,等.BP网络和RBF网络用于输电线路故障定位比较[J].中国电力教育,2010,33(184):259-262.
[22] 谌爱文.基于BP和RBF神经网络的数据预测方法研究[D].长沙:中南大学,2007.

相似文献/References:

[1]邵金花,刘贤赵.烟台市水资源承载力的RBF神经网络评价法[J].水土保持研究,2007,14(06):115.
　SHAO Jin-hua,LIU Xian-zhao.Comprehensive Evaluation on Water Resources Carrying Capacity in Yantai City Based on Radial Basis Function Neural Network[J].Research of Soil and Water Conservation,2007,14(02):115.

备注/Memo

收稿日期:2012-08-28;改回日期:2012-10-27。
基金项目:国家自然科学基金资助项目（41072171）；水利部“948”计划项目（201122）
作者简介:伊燕平(1984-),女,吉林长春人,博士研究生,助理工程师,主要从事地下水数值模拟研究。E-mail:yiyanping-101@163.com
通讯作者:卢文喜(1956-),男,吉林德惠人,教授,主要从事地下水数值模拟与优化管理等研究。E-mail:Luwenxi@jlu.edu.cn

更新日期/Last Update: 1900-01-01