针对林隙大小的时变性、不确定性，及林隙大小与其影响因素存在复杂的非线性关系,采用改进的Elman神经网络对林隙大小建立动态模型。在分析改进的Elman神经网络结构特点、改进算法及训练过程的基础上，选择庞泉沟自然保护区内华北落叶松林、油松林、云杉林为对象,建立了基于改进的Elman神经网络林隙大小动态预测模型。结果表明:所建模型对林隙大小的拟合仿真具有很高的精度，预测效果比较稳定。最后运用此模型预测了3种林分对应调查林隙被填充者完全取代的年限。
Abstract
A dynamic model for forecasting forest gap size was established using a modified Elman neural network for overcoming the disadvantage of timevariability, uncertainty, and complex nonlinear relationship with its impact factor of forest gap size. Firstly, the structural features, mathematical model and learning algorithm of the modified Elman neural network were examined, and a dynamic model for forecasting forest gap size was then set up based on the modified Elman neural network by selecting Larix principisrupprechtii, Spruce, Pinus tabulaeformis forest in Pangquangou Nature Reserve as the test objects. The fitting and simulation results showed that the established prediction model is feasible to forest gap size, and three kinds of forest gaps were lastly investigated using this model
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］臧润国,郭忠凌,高文韬.长白山自然保护区阔叶红松林林隙更新的研究［J］.应用生态学报,1998,9(4)∶349-353.
［2］吴刚.长白山红松阔叶林林冠空隙特征的研究［J］.应用生态学报,1997,8(4):360-364.
［3］Botkin D B,Janak J F,Wallis J R. Some ecological consequences of a computer model of forest growth［J］.Journal of Ecology,1972,60(3):849-872.
［4］Shugart H H.A Theory of Forest Dynamics:The Ecological Implications of Forest Succession Models［M］.New York:Springer,1984.
［5］Runkle J.Comparison of methods for determining fraction of land area in treefall gaps［J］.Forest Science,1985,31 (1):15-19.
［6］Whitmore T C. Canopy gaps and the two major groups of forest trees［J］.Ecology,1989,70:536-538.
［7］赵秀海,张春雨,郑景明.长白山阔叶红松林林隙大小结构研究［J］.北京林业大学学报,2006,28(4):34-38.
［8］闫淑君,洪伟,吴承桢.中亚热带常绿阔叶林林隙面积的Weibull分布模型研究［J］.江西农业大学学报:自然科学版,2002,24(6):802-805.
［9］张乃尧,阎平凡.神经网络与模糊控制［M］.北京:清华大学出版社,1998.
［10］段东兴,孙伟,何玉钧.基于蚁群聚类-Elman神经网络模型的短期电力负荷预测［J］.中国电力,2006,39(7):49-51.
［11］陈伟韦,卢文喜,柳大伟,等.Elman神经网络在地下水动态预测中的应用［J］.吉林大学学报:地球科学版,2006(增刊):52-55.
［12］张兴会,杜升之,陈增强,等.基于对角Elman神经网络的失业预测模型［J］.南开大学学报:自然科学版,2006,35(2):60-64.
［13］王伟.人工神经网络原理:入门与应用［M］.北京:北京航空航天大学出版社,1995.
［14］Maqsood I, Khan M R, Huang G H, et al.Application of soft computing models to hourly weather analysis in southern Saskatchewan,Canada［J］.Engineering Applications of Artificial Intelligence,2005,18(1):115-125.
基金
收稿日期：2010-05-28修回日期：2010-12-07基金项目：国家自然科学基金项目(10671032)作者简介：符利勇（1984—）,博士生。*刘应安（通信作者）,教授。Email:lyastat@njfu.edu.cn。引文格式：符利勇， 何铮， 刘应安. 基于改进Elman神经网络的林隙大小预测模型［J］. 南京林业大学学报:自然科学版,2011,35(3):28-32.
PDF(1186404 KB)
