BP-MSM混合算法及其在森林自疏规律研究中的应用

应用生态学报 ›› 2000, Vol. 11 ›› Issue (5): 655-659.

BP-MSM混合算法及其在森林自疏规律研究中的应用

吴承祯, 洪伟

福建林学院资源与环境学系, 南平353001

收稿日期:1999-03-19 修回日期:1999-07-19 发布日期:2000-09-25
通讯作者: 吴承祯,1970年生,博士,副教授.主要从事数量生态学与森林生态学等领域教学与科研.发表学术论文80余篇.E-mail:zjwucz@public.npptt.fj.cn E-mail:zjwucz@public.npptt.fj.cn
基金资助:
福建省自然科学基金资助项目(F991)

Neural network based on modified simplex method and its application in studying forest self-thinning

WU Chengzhen, HONG Wei

Department of Resources and Environment, Fujian Forestry College, Nanping 353001

Received:1999-03-19 Revised:1999-07-19 Published:2000-09-25

摘要/Abstract

摘要： 森林自然稀疏机制一般是非线性的、动态的.人工神经网络具有逼近任意非线性映射的特性.本文阐述了人工神经网络模拟森林自疏机制的可行性和不足之处,并提出了基于改进单纯形法的神经网络模型(BP-MSM混合算法)的基本原理和算法,结合山杨天然林和杉木人工林自疏实例说明了其应用.森林自疏实例应用结果表明,BP-MSM混合算法模拟森林自然稀疏机制是理想的,模拟精度较高,从而继承和发展了人工神经网络方法与理论,丰富了森林自然稀疏规律研究方法.

关键词: 改进单纯形, 神经网络, 自疏规律, BP-MSM混合算法, 沙柳, 柠条, 降雨改变, 茎水力学特性

Abstract: The mechanism of forest self-thinning is generally nonlinear and dynamic,and the artificial neural network has the characteristic of expressing arbitrary nonlinear mapping.In this paper, the feasibility and limitation of artificial neural network used to simulating forest self-thinning was expounded,and the principle and algorithms of the neural network model based on modified simplex method (BP-MSM mixed algorithms) for modeling forest self-thinning were described.Its applications in self-thinning of Populus tremula natural forest Cunninghamia lanceolata plantation were illustrated. The results of forest self-thinning examples show the BP MSM mixed algorithms were satisfactory in simulating forest self-thinning,and its precision was higher, which develops the method and theory of artificial neural network,and enriches the simulating method of forest self-thinning.

Key words: Modified simplex method, Artificial neural network, self-thinning, BP-MSM mixed algorithms, precipitation variation., stem hydraulic trait, Caragana korshinskii, Salix psammophila

吴承祯, 洪伟. BP-MSM混合算法及其在森林自疏规律研究中的应用[J]. 应用生态学报, 2000, 11(5): 655-659.

WU Chengzhen, HONG Wei. Neural network based on modified simplex method and its application in studying forest self-thinning[J]. Chinese Journal of Applied Ecology, 2000, 11(5): 655-659.

参考文献

1 Dong M(董鸣). 1987.A preli mi nary study of the age structure of Masson pine population at Jinyun mountain.A cta Phytoecol et Geobot(植物生态学与地植物生态学学报),11(1): 28～35 (in Chinese)

2 Fang J-Y(方精云). 1995.An empirical model describing natural thinning process of plant population. Scientia Silvae Sinicae(林业科学),31(3):247～252(in Chinese)

3 Happer JL.1977.Population Bi ology of Plants.London:Academic Press.20～89

4 Hechi-Nielsen R. 1989.Theory of back propagation neural network. Int J Conf Neural Network,(1):593～605

5 Hong W(洪伟) Wu C-Z(吴承祯) He D - J(何东进). 1998.A study on the model of forest resources management based on the artificial neural network.J Nat Resour(自然资源学报),13(1):69～73(in Chinese)

6 Hozumi K.1977.Ecological and mathemat ical considerations on self-thinning in even-aged pure stands I. Mean plant w e ight density trajectory during the course of self-thinning.Bot Mag Tokyo, 90:165～179

7 Hozumi K.1983.Ecological and mathema t ical considerations on self-thinning in ever-aged pure stands III. Effect of t he linear growth factor on self-thinning.Bot Mag Tokyo,96[ WTBZ :171～191

8 Hutchings M L.1983.Ecological laws i n search of a theory.New scientist,98:765～76 7

9 Jiao L-C(焦李成). 1993.The Applicati on and Achieving of Neural Network.Xian:Xian Electronic Science and Technology U niversity Press.87～125(in Chinese)

10 Liang H-L(梁化楼). 1995.The combinat ion of artificial neural network and genetic algorithm:The present condition and development.J Electronics (电子学报),23(10) :194～199(in Chinese)

11 Nielsen RH. 1987.Kolmogorov's neural mappin g network existence theory.San Diego:Proc. IEEE First International Conference o n Neural Networks, (3):11～14

12 Shi P-L(石培礼) Yang X(杨修) Zhong Z-C (钟章成).1997.Dynamics of population biomass and its density-dependent regulatio n in alder and cypress mixed forest.Chin J Appl Ecol(应用生态学报), 8(4):341～346(in Chinese)

13 Tang S-Z(唐守正). 1993.The research of self -thinning law for even-aged pure stands. Scientia Silvae Sinicae(林业科学),29(3):234～241(in Chinese)

14 Wu C-Z(吴承祯) Hong W(洪伟) He D-J(何东进).1999.Study on density change law in alder and cypress mixed forest by arti f icial neural network.Acta Bot Boreali-Occid Sin(西北植物学报),19(1):144～150(in Chinese)

15 Wu C-Z(吴承祯) Hong W(洪伟).1999. A stud y of optimum fitting Logistic curve by modified simplex method.J Biomath(生物数学学报),14(1):25～29(in Chinese)

16 Wu C-Z(吴承祯) Hong W(洪伟). 1998.A stud y on optimum fitting of Taylor's power law model by modified simplex method.J In ner Mongolia Fore Coll(内蒙古林学院学报),20(2) : 20～24(in Chinese)

17 Yada K,Kira T,Qgawa H.1963.Self-thinning i n overcrowded pure stands under cultivated and natural conditions.J Biol (14):107～129

18 Zhao X-N(赵学农). 1991.A preliminary study o f the regulation and competition of the dominant plant populations in Xujiaba re gion,Ailao Mts Tunnan.Acta Phytoecol et Geob Sin(植物生态学与地植物生态学学报),15(2):183～189(in Chinese)

19 Zhao Y-D(赵远东) Guo G(郭光),Yan X-J(严绍瑾). 1997.Timeseries prediction model from the combination of artificial neural ne twork and genetic algorithm.J Nanjing Inst Meteor(南京气象学院学报), 20(3): 375～381(in Chinese)

20 Zhang D-Y(张大勇) Zhao S-L(赵松龄).1985.S tu dies on the model of forest population density change during self-thinning. S cie ntia Silvae Sinicae(林业科学),21(4):369～374(in Chinese)

21 Zhang Z-Q(庄镇泉). 1992.Neural Network and Neural Computer.Beijing:Science Press.7～51(in Chinese)

22 Zhang L-Q(张利权).1990.The age stru cture and spatial pattern of population of Pinus taiwanensis in Songyang county,Zheji ang province.Acta Phytoecolo et Geob Sin(植物生态学与地植物生态学学报),14(4):328～334(in Chinese)

[1]	巴音吉, 刘琳奇, 彭青, 张功, 陆森, 罗坤水, 张劲松. 作物水分胁迫指数模型中下限温度的参数化:以栓皮栎人工林为例 [J]. 应用生态学报, 2024, 35(7): 1866-1876.
[2]	蔡斌, 董瑞, 花蕊, 刘济泽, 王磊, 郝媛媛, 杨思维, 花立民. 基于无人机影像的鼠害地秃斑识别算法筛选 [J]. 应用生态学报, 2024, 35(7): 1951-1958.
[3]	王嘉浩, 朱凯, 徐开达, 王好学, 陈睿毅, 曾佳颖. 基于耳石形态判别舟山海域条石鲷自然群体和养殖群体 [J]. 应用生态学报, 2024, 35(11): 3165-3173.
[4]	王国华, 王佳琪, 刘婧. 晋西北丘陵风沙区柠条锦鸡儿人工林植被和土壤随林龄变化特征 [J]. 应用生态学报, 2024, 35(1): 62-72.
[5]	孙龙, 马灵感, 郭妍, 范佳乐, 陈伯轩, 胡同欣. 基于卷积神经网络及气象要素回归法的地表死可燃物含水率预测模型 [J]. 应用生态学报, 2023, 34(9): 2453-2461.
[6]	周鹏, 韩磊, 彭苓, 柳利利, 王娜娜, 马军, 马云蕾. 基于神经网络优化模型的丝绵木瞬态液流模拟 [J]. 应用生态学报, 2023, 34(8): 2123-2132.
[7]	冯子欣, 孙欣彤, 薛领, 张天骄. 国家公园类型划分与空间识别——以云南省为例 [J]. 应用生态学报, 2023, 34(1): 187-195.
[8]	高欣, 杨立新, 陈振举. 基于树木年轮径切特征的卷积神经网络树种识别 [J]. 应用生态学报, 2023, 34(1): 47-57.
[9]	崔晏华, 刘淑德, 张云雷, 徐宾铎, 纪毓鹏, 张崇良, 任一平, 薛莹. 海州湾春季短蛸的栖息分布特征及其与环境因子的关系 [J]. 应用生态学报, 2022, 33(6): 1686-1692.
[10]	缑倩倩, 高敏, 张宇, 王国华. 晋西北丘陵风沙区不同种植年限柠条的种子形态特征 [J]. 应用生态学报, 2022, 33(11): 2907-2914.
[11]	邱吉丽, 张弥, 蒲旖旎, 张圳, 贾磊, 赵佳玉, 肖薇, 刘寿东. 涡度相关观测的太湖CH₄通量数据插补方法评价 [J]. 应用生态学报, 2022, 33(10): 2785-2795.
[12]	梁瑞婷, 王轶夫, 邱思玉, 孙玉军, 谢运鸿. 人工神经网络与相容性生物量模型预测单木地上生物量的比较 [J]. 应用生态学报, 2022, 33(1): 9-16.
[13]	王国华, 宋冰, 席璐璐, 缑倩倩. 晋西北丘陵风沙区不同林龄人工柠条生长与繁殖动态特征 [J]. 应用生态学报, 2021, 32(6): 2079-2088.
[14]	侯青青, 裴婷婷, 陈英, 吉珍霞, 谢保鹏. 1986—2019年黄土高原干旱变化特征及趋势 [J]. 应用生态学报, 2021, 32(2): 649-660.
[15]	韩永贵, 高阳, 韩磊, 黄晓宇. 基于模糊规则的人工神经网络模拟新疆杨蒸腾耗水 [J]. 应用生态学报, 2020, 31(5): 1525-1534.