| BP神经网络反演森林生物量模型研究 |
| |
| 引用本文： | 李丹丹,冯仲科,汪笑安,张凝,张巍巍.BP神经网络反演森林生物量模型研究[J].林业调查规划,2013,38(1):5-8. |
| |
| 作者姓名： | 李丹丹 冯仲科 汪笑安 张凝 张巍巍 |
| |
| 作者单位： | 北京林业大学3S技术中心,北京,100083 |
| |
| 摘 要： | 基于LandsatTM影像和DEM数据，尝试利用BP神经网络建立旺业甸林场森林生物量非线性遥感模型系统，通过实验筛选，最终利用增强型的BP网络进行训练仿真。模型仿真结果表明，增强型的BP神经网络具有自学习和自适应功能强、收敛速度快的特点，能够最大限度地利用先验样本。仿真检验结果的相对系数达0．8022，平均相对误差为15．7％，表明该模型预测的生物量与实际生物量一致性较好，能够达到较好的反演效果。
|
| 关 键 词： | 森林生物量 模型 BP神经网络 反演 |
Model of BP Neural Network Inversing Forest Biomass |
| |
| LI Dan-dan
,
FENG Zhong-ke
,
WANG Xiao-an
,
ZHANG Ning
,
ZHANG Wei-wei.Model of BP Neural Network Inversing Forest Biomass[J].Forest Inventory and Planning,2013,38(1):5-8. |
| |
| Authors: | LI Dan-dan FENG Zhong-ke WANG Xiao-an ZHANG Ning ZHANG Wei-wei |
| |
| Institution: | (Institute of GIS,RS&GPS,Beijing Forestry University,Beijing,100083,China) |
| |
| Abstract: | Based on Landsat TM images, DEM data, and using BP neural network, this study established Wangyedian forest farm biomass non-linear remote sensing model system. Choosing by experiment and taking enhancement mode of BP network, simulation training has been conducted. The results showed that： the enhancement model of BP neural network has characteristics of self-learning, strong adaptive and fast convergence . It could maximum use prior sample, and relative coefficient reached to 0. 802 2, the average relative error was 15.7%. This model also had great consistency of predicted biomass and actual biomass, could achieve better inversion effect. |
| |
| Keywords: | forest biomass model BP neural network inversion |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
