基于BP神经网络的泉州湾红树株高预测模型

Prediction of height of Quanzhouwan mangroves based on BP neural networks

在分析测量数据的基础上,提取红树的平均基径、基径数、平均胸径、胸径数等特征参数,建立了预测红树株高的人工神经网络模型。采用Levenberg-Marquardt优化算法改进了BP神经网络算法;采用训练好的BP神经网络模型对距堤坝25,50,75 m 3个采样点的株高进行预测,预测值和实测值的均方根误差分别为0.000 6,0.002 2,0.004 1,相关系数分别为0.99,0.95,0.94。结果表明利用BP神经网络对红树株高进行预测是可行的。

Based on the test data analysis method, characteristic parameters of mangroves,i, e. average basal diameter, the number of basal diameter, average diameter at breast-high （DBH） , the number of DBH were extracted, and the artificial neural network model was developed to predict the height of mangroves. The back propagation（BP） algorithm was improved by using the Levenberg-Marquardt optimizing arithmetic. The heights of mangroves in the sampling points which are 25,50 and 75 m away from the dam were predicted using the trained BP neural network, standard errors are 0. 000 6,0. 002 2 and 0. 004 1 ,with the correlation coefficients of 0. 99,0. 95 and 0. 94. Results show that using BP neural network to predict the height of mangroves is feasible.