Assessing Forest/Non-Forest Separability Using Sentinel-1 C-Band Synthetic Aperture Radar
Assessing Forest/Non-Forest Separability Using Sentinel-1 C-Band Synthetic Aperture Radar
复制标题
DOI：
10.3390/rs12111899
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Johannes N. Hansen;E. Mitchard;Stuart King
中科院分区：
文献类型：
--
作者：
Johannes N. Hansen;E. Mitchard;Stuart King
合成孔径雷达在连续森林测绘方面具有独特的潜力，因为它不受云层覆盖的影响。虽然较长的波长，如L波段，通常用于森林应用，在本文中，我们评估的能力，C波段哨兵-1数据为此目的，有很大的兴趣，由于其高的时间分辨率（5天）和“免费，完整，开放”的数据政策。我们测试了它的能力，区分森林和非森林在六个研究地点，位于阿拉斯加，哥伦比亚，芬兰，佛罗里达，印度尼西亚和英国。与单一场景相比，使用全年的时间序列显着提高了分类准确性（最佳分类器的平均值为85%，而整个研究地点的平均值为77%）。结果表明，仅考虑共极化（VV）和交叉极化（VH）后向散射的年平均值和标准差，可以进一步提高平均精度到87%。在这种情况下，分离精度高达93%（在芬兰）是可能的，尽管在最坏的情况下（阿拉斯加），使用这些变量的最高可能精度为80%。当使用支持向量机分类器时，观察到最佳的整体性能，优于随机森林，k-最近邻和二次判别分析。我们进一步表明，我们在相位数据中发现的小信息内容是地形坡度方向的伪影，对分类器性能的影响可以忽略不计。我们的结论是，森林映射的目的，较小的文件大小和更容易处理GRD产品是足够的，除非SLC产品用于计算时间的一致性，这是在这项研究中没有测试。
Synthetic Aperture Radar has a unique potential for continuous forest mapping as it is not affected by cloud cover. While longer wavelengths, such as L-band, are commonly used for forest applications, in this paper we assess the aptitude of C-band Sentinel-1 data for this purpose, for which there is much interest due to its high temporal resolution (five days) and “free, full, and open” data policy. We tested its ability to distinguish forest from non-forest in six study sites, located in Alaska, Colombia, Finland, Florida, Indonesia, and the UK. Using the time series for a full year significantly increases the classification accuracy compared to a single scene (a mean of 85 % compared to 77 % across the study sites for the best classifier). Our results show that we can further improve the mean accuracy to 87 % when only considering the annual mean and standard deviation of co-polarized (VV) and cross-polarized (VH) backscatter. In this case, separation accuracies of up to 93 % (in Finland) are possible, though in the worst case (Alaska), the highest possible accuracy using these variables was 80 % . The best overall performance was observed when using a Support Vector Machine classifier, outperforming random forest, k-Nearest-Neighbors, and Quadratic Discriminant Analysis. We further show that the small information content we found in the phase data is an artifact of terrain slope orientation and has a negligible impact on classifier performance. We conclude that for the purposes of forest mapping the smaller file size and easier to process GRD products are sufficient, unless the SLC products are used to compute the temporal coherence which was not tested in this study.