摘要:以北亚热带湖北省太子山林场为研究对象，基于高空间分辨率GF-2与SPOT-6卫星影像，提取不同窗口大小下的纹理信息与光谱信息，利用随机森林回归算法，并结合野外实测106块样地的生物量数据，建立不同影像下的太子山林场森林生物量反演模型。结果显示：（1） GF-2和SPOT-6虽然空间分辨率有差异，但是从其不同波段反射率的相关系数（0.75、0.78、0.73、0.61）发现，两种影像的波段反射率具有较高的相关性，说明两者的辐射性能相近；（2）通过分析不同纹理特征对生物量模型的影响，发现均值和对比度纹理参数对生物量反演具有很好的效果。（3）高分辨率的遥感数据在生物量反演中具有较好的表现，且GF-2生物量模型精度（R²=0.88，RMSE=27.11 Mg/hm²）与SPOT-6生物量模型的精度（R²=0.89，RMSE=23.93 Mg/hm²）相近。（4）两种影像对不同森林类型的生物量预测值不存在显著差异，都适合对不同林分类型的生物量进行预测。



Abstract:Taking Taizishan Forest Farm in Hubei Province as the study area and using GF-2 and SPOT-6 satellite images as the data source, texture features under different window sizes and spectral features were extracted. Using random forest algorithm and Taizishan forest data obtained by field investigation, we construct forest biomass inversion model. The results show that (1) although the spatial resolution of GF-2 and SPOT-6 are different, the correlation coefficients (0.75, 0.78, 0.73, 0.61) of the reflectance of different wavebands indicate that the waveband reflectance of the two images is relatively high. The high correlation indicates that the radiation performance of the two is similar. (2) By analyzing the influence of different texture features on the biomass model, it is found that the mean and contrast values have a good effect on biomass inversion. (3) High resolution remote sensing data has a good performance in biomass retrieval, and the accuracy of the GF-2 biomass model (R²=0.88, RMSE=27.11 Mg/hm²) and the SPOT-6 biomass model (R²=0.89, RMSE=23.93 Mg/hm²) is similar. (4) The two images have no significant differences in the biomass prediction values of different forest types, and both are suitable for predicting the biomass of different forest types.





PDF全文下载地址:

https://www.ecologica.cn/stxb/article/pdf/stxb201910082086