| ANN在森林资源预测中的应用研究 |
| |
| 引用本文： | 张锦宗,朱瑜馨.ANN在森林资源预测中的应用研究[J].干旱区研究,2004,21(4):374-378. |
| |
| 作者姓名： | 张锦宗 朱瑜馨 |
| |
| 作者单位： | 聊城大学,环境与规划学院,聊城,252059 |
| |
| 基金项目： | 宁夏自治区林业厅资助项目 |
| |
| 摘 要： | 人工神经网络(ANN)方法是基于实例的方法,不需要考虑数学模型的内部结构,不需要假设前提条件,不需要人为地确定因子权重,作为一个黑箱综合地映射研究对象的整体性。应用人工神经网络多步预测方法对甘肃连城林场吐鲁沟营林区有林地面积进行预测,网络模型的最大相对误差为0 080 8％,最小相对误差达到0 0089％,平均为0.038 6％,表明预测值与实际值吻合程度很好,因此模型的精度较高,并且建模简单经预测,林场2000-2004年有林地面积稍有下降趋势,分别为2 873.2 hm2,2 618 7 hm2,2 484.5 hm2,2 346 hm2,2 171 6hm2。
|
| 关 键 词： | 森林资源 预测 ANN |
| 文章编号： | 1001-4675(2004)04-0374-05 |
Study on the Application of ANN in the Prediction of Forest Resources |
| |
| ZHANG Jin-zong ZHU Yu-xin.Study on the Application of ANN in the Prediction of Forest Resources[J].Arid Zone Research,2004,21(4):374-378. |
| |
| Authors: | ZHANG Jin-zong ZHU Yu-xin |
| |
| Abstract: | Artificial never network (ANN) is a method based on the observation, it does not need to deal with the internal relations and structures of mathematical models and define the factor weights, nor the assumed premises, and it is regarded as a black box to synthetically refer the integration of the objects. In this paper, the area of woodlands in the Tulugou forest area of Liancheng Forestry Center, Gansu Province, is predicted by us ing ANN, and the maximum, minimum and average relative errors of the ANN model are 0. 080 8%, 0.008 9% and 0.038 6% respectively. These reveal that the predicted values accord well with the actual ones, so a high precision can be achieved by using the ANN model, and it is easy to develop a model According to the prediction, the change of the area of woodlands in the forestry center is not so obvious, and the areas of wood lands are 2873.2 hm2, 2618.7 hm2, 2484.5 hm2, 2 346.0 hm2 and 2 171.6 hm2 in 2000, 2001, 2002, 2003 and 2004 respectively. |
| |
| Keywords: | forest resources prediction ANN |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
