摘要
杉木是我国南方最重要的速生丰产树种，在人工林中具有十分重要的地位，但是杉木种子涩籽率高是影响杉木产量和发展的主要原因之一，因此，积极探讨杉木种子涩籽的预测与防治是杉木种子生产中亟待解决的问题。而不同的地域是造成杉木种子涩籽量差异的重要因子之一，为了进一步探讨杉木种子涩籽在地理上的流行规律，本文试图运用一种新的方法———人工神经网络方法对杉木种子涩籽与地理之间的关系进行研究，建立了杉木种子涩籽地理流行ＢＰ网络模型。结果表明：所建立的ＢＰ 模型对模拟预测不同地域杉木种子涩籽的涩籽率具有较高的精度，平均模拟精度为８８－４０ ％ 。这不仅为杉木种子园的合理布局提供理论依据。
Chinese fir is the most important fast\|growing and high\|yield tree species in southern China, it occupies a very significant position in Chinese plantation management. However, the rate of sterile seeds of Chinese fir is high, for example in Fujian Province, which seriously affects the production and development of Chinese fir. So it is an urgent problem to study the prediction and prevention of sterile seeds in the production of Chinese fir seeds. For the sake of revealing the epidemic law of sterile seeds, this paper studied the relationships between Chinese fir sterile seeds and geographic epidemic by a new method-artificial neural network.\;Artificial neural network is a good method in handling the overall nonlinear mapping problems between input variables and output ones, which has a wide application in many research fields such as system simulating, automation controlling, paralled data processing and so on. In this paper, the authors selected BP artificial neural network to deal with the relationships between Chinese fir sterile seeds and geographic epidemic, where the input variables are longitude and latitude, the output variable is rate of sterile seeds of Chinese fir, the number of neurons of hidelevel(\%M\%) is \%M=2L+1\% according to document(\%L\% is the number of factors of input\|level), and the network activity function is Sigmiod function as follows: F(x)=1/(1+e\+\{-x\} ). Using the built BP network, the samples were trained until E\-j(W\+1\-\{lm\},W\+2\-\{mn\})=∑Nn=1(O\-\{nj\}-Y\-\{nj\})\+2 =min,where O\-\{nj\} and Y\-\{nj\} are output values of network and real values of rate of Chinese fir sterile seeds respectively, N is the number of trained samples, and E\-j is sum of square deviation of BP network. If E\-j didn't converge, the weights and thresholds of BP network were adjusted as follows: ΔW\-\{ij\}(n+1)=βλ\-jX\-i+αΔW\-\{ij\}(n) and Δη\-j(n+1)=-βλ\-j+αΔη\-j(n) . The results showed that the accuracy of BP model in simulating the epidemic rat
出处
《林业科学》
EI
CAS
CSCD
北大核心
1999年第6期58-62,共5页
Scientia Silvae Sinicae
关键词
杉木
涩籽
地理流行
BP网络
种子
Chinese fir, Sterile seed, Geographic epidemic, BP network \
