基于BP网络的典型草原群落自然演替预测模型研究

doi:10.11733/j.issn.1007-0435.2008.03.008

›› 2008, Vol. 16 ›› Issue (3): 251-255.DOI: 10.11733/j.issn.1007-0435.2008.03.008

基于BP网络的典型草原群落自然演替预测模型研究

冯全¹, 邵新庆², 王赟文²

1. 甘肃农业大学, 甘肃, 兰州, 730070;
2. 中国农业大学动物科技学院, 北京, 100193

收稿日期:2008-01-15 修回日期:2008-03-19 出版日期:2008-06-15 发布日期:2008-06-15
通讯作者: 邵新庆
作者简介:冯全(1969- ),男,四川人,博士,主要从事农业信息研究,E-mail:fquan@sina.com
基金资助:
农业部公益性行业科研专项(nyhyzx07-022)

Studies on Natural Succession Prediction of Typical Steppe Based on BP-NN

FENG Quan¹, SHAO Xin-qing², WANG Yun-wen ²

1. Gansu Agricultural University, Lanzhou, Gansu Province 730070, China;
2. Department of Grassland Science, College of Animal Science and Technology, China Agricultural University, Beijing 100193, China

Received:2008-01-15 Revised:2008-03-19 Online:2008-06-15 Published:2008-06-15

摘要/Abstract

摘要： 以典型草原植被群落为研究对象,探讨草地生态系统自然演替恢复的动态变化,采用BP人工神经网络,以演替年度为输入量,群落的凋落物、含水量、容重、孔隙度、有机质、微生物量C、土壤N、地上生物量和多年生禾草密度为输出量,对典型草原群落自然演替进程进行模拟和预测.结果表明:BP-NN的稳定性较好,各参数预测结果的平均误差为2.04%,说明BP-NN可适用预测典型草原群落自然恢复演替,其优势在于可模拟了解较少或不确定性和模糊性较大的系统行为,这是传统数学模型所无法实现的,因而是对传统机理模型的重要补充.

关键词: 典型草原, 人工神经网络, 自然演替, 预测

Abstract: Focusing on the natural restoration of typical steppe community,the dynamic progress of the natural restoration and succession of the steppe was studied using BP neural network.Several representative community parameters,i.e.litter biomass,soil water content,soil bulk density,soil porosity,soil organic matter,soil microbial biomass C,soil total N,aboveground biomass,and perennial grass density,in the succession were simulate and predicted by BP-NN.The results of emulational experiment show that BP-NN had very good stability and the average prediction error was 2.04% and those indicate that BP-NN is viable to forecast the self-organized succession of typical steppe community.The advantage of artificial neural network lies on its ability to precisely simulate the vaguely understood and uncertain systemic behavior which cannot be realized by the traditional approaches.As a nonlinear approximator,artificial neural network would be an important tool complementary to the comprehensive models.

Key words: Typical steppe, Artificial neural network, Natural succession, Prediction

中图分类号:

S812
TP39

冯全, 邵新庆, 王赟文. 基于BP网络的典型草原群落自然演替预测模型研究[J]. , 2008, 16(3): 251-255.

FENG Quan, SHAO Xin-qing, WANG Yun-wen . Studies on Natural Succession Prediction of Typical Steppe Based on BP-NN[J]. , 2008, 16(3): 251-255.

0
/ / 推荐

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://manu40.magtech.com.cn/Jweb_cdxb/CN/10.11733/j.issn.1007-0435.2008.03.008

https://manu40.magtech.com.cn/Jweb_cdxb/CN/Y2008/V16/I3/251

参考文献

[1] 郭新宇.作物生育动态的全息协调神经网络研究[D] :[学位论文].北京:中国农业大学,2001
[2] James F C,McCulloch C E.Multivariate analysis in ecology and systematics[J].Annual Review of Ecology and Systematics,1990,21 (6):192-196
[3] 阎平凡,黄端旭.人工神经网络-模型、分析与应用[M].合肥:安徽教育出版社,1993.55
[4] Hornik K,Stinchcombe M,White H.Miltilayer feedforward networks are universal approximators[J].Neural Networks,1989,12 (2):359-366
[5] 张志鹏,曹庆波,文新亚.应用人工神经网络方法评定作物生产系统中指标的权重[J].农业系统科学与综合研究,2003,24(2),1-4
[6] Rumethart D,Hinfon G,Williams R.Learning representation by back propagating errors[J] Nature.1986,323:533-536
[7] Elizondo D A,McClendon R W,Hoogenboom G L Neural net work models for predicting flowering and physiological maturity of soy bean[J].Transactions of the ASAE,1994,37 (3):981-988
[8] Major D J,Hill B D,Toure A.Prediction date in southern Alberta[J].Canadian J.of Plant Science,1996,76 (8):59-65
[9] Bochereau L,Bourgine P,Palagos B.A method for prediction by combling data analysis and neural net works[J].Agri.Eng.Res.,1992,51 (2):207-216
[10] 文新辉,陈开周.一种新的昆虫神经网络预测预报方法[J].系统科学与数学,1995,13(2):9-13
[11] 浦瑞良,宫鹏.应用神经网络和多元回归技术预测森林产量[J].应用生态学报,1999,10(2):129-134
[12] 蔡煜东,汪列,甘骏人.羊草草地放牧演替阶段的人工神经网络分析方法[J].中国草地,1995,16(1),6-9
[13] 王丽娟,李青丰,根晓.禁牧对巴林右旗天然草地生产力及植被组成的影响[J].中国草地,2005,27(3):11-15
[14] 周景云,乌云,建原.禁牧舍饲对草原植被恢复的作用[J].内蒙古草业,2003,15(1):40-42
[15] Schnltz A,Wieland R,Lutze G.Neural networks in agrecological modeling-stylish application or helpful tool[J].Computer and Electronics in Agriculture,2000,29 (8):73-97
[16] Gob A T.Back-propagation neural networks for modeling complex systems[J].Artifical intelligence in Engineering,1995,27 (9):143-151
[17] 刘景玲,高玉葆,何兴东,等.内蒙古中东部草原植物群落物种多样性和稳定性分析[J].草地学报.2006,14(4):390-392
[18] 汪诗平.天然草原持续利用理论和实践的困惑[J].草地学报,2006,14(2),188-192

基于BP网络的典型草原群落自然演替预测模型研究

Studies on Natural Succession Prediction of Typical Steppe Based on BP-NN

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	裴雯, 陈清, 张洛梓, 贾丽英. 放牧、水分和氮素对内蒙古草原土壤团聚体的影响[J]. 草地学报, 2021, 29(7): 1499-1506.
[2]	杨建强, 曹梦琪, 王袼, 胡姝娅, 王常慧. 内蒙古不同类型草地土壤氨氧化细菌和古菌的比较研究[J]. 草地学报, 2021, 29(12): 2664-2669.
[3]	何源, 李星锐, 杨晓帆, 唐海萍. 内蒙古锡林郭勒盟典型草原固碳量及固碳潜力估算[J]. 草地学报, 2021, 29(10): 2274-2285.
[4]	张紫薇, 高斌, 林长存, 王青, 刘佳乐, 杨娜, 苏德荣, 平晓燕. 放牧强度对典型草原6个物种生物量分配格局的影响[J]. 草地学报, 2021, 29(1): 149-155.
[5]	王秀梅, 董建军. 基于广义线性模型估算内蒙古荒漠草原及典型草原地上生物量变化[J]. 草地学报, 2020, 28(6): 1711-1718.
[6]	宋洁, 王凤歌, 温璐, 王立新, 李金雷, 武胜男, 徐智超. 放牧对温带典型草原植物物种多样性及土壤养分的影响[J]. 草地学报, 2019, 27(6): 1694-1701.
[7]	李文龙, 魏巍, 宋瑜, 刘陈立, 苏文亮, 许静, 朱高峰. 基于能值生态足迹与灰色预测模型的西藏可持续性评价[J]. 草地学报, 2019, 27(3): 702-710.
[8]	李梦琦, 何兴东, 杨祥祥, 丁新峰, 赵月丹, 高玉葆, 尤万学, 余殿, 蔡莉. 半干旱区两种草原类型植物体内草酸钙研究[J]. 草地学报, 2018, 26(6): 1421-1427.
[9]	董瑞兰, 贾婉, 于光辉. 草地产草量和动物承载力预测模型研究进展[J]. 草地学报, 2018, 26(5): 1043-1051.
[10]	李艳龙, 石椿珺, 程建伟, 郭旭东, 张桐瑞, 李永宏. 内蒙古典型草原三种家畜采食量和食性选择的研究[J]. 草地学报, 2018, 26(5): 1091-1096.
[11]	邬嘉华, 王立新, 张景慧, 卓义, 武胜男, 王凤歌, 徐智超, 祁瑜, 温璐. 温带典型草原土壤理化性质及微生物量对放牧强度的响应[J]. 草地学报, 2018, 26(4): 832-840.
[12]	侯东杰, 乔鲜果, 高趁光, 赵海卫, 赵利清, 郭柯. 内蒙古典型草原枯落物的生态水文效应[J]. 草地学报, 2018, 26(3): 559-565.
[13]	陈学平, 杨艳刚, 尚占环, 陈济丁, 孔亚平, 王九峦. 青藏高原公路两侧草地土壤种子库特征研究—以国道214公路共玉公路段为例[J]. 草地学报, 2018, 26(1): 85-91.
[14]	王玺, 贾丽欣, 乔荠蓉, 杨阳, 张峰, 赵萌莉. 留茬高度对典型草原大针茅种群特征影响的研究[J]. 草地学报, 2018, 26(1): 92-98.
[15]	达布希拉图, 彭菲, 林杉. 内蒙古典型草原主要物种-土壤互反馈初探[J]. 草地学报, 2016, 24(6): 1184-1191.