Fractional tree cover facilitates the characterization of forest cover changes using satellite data. However, there are still substantial challenges in generating fractional tree cover datasets that satisfy the requirements of interannual stability for forest cover change monitoring. In this study, a global annual fractional tree cover dataset, named as GLOBMAP Fractional Tree Cover, was generated from MODIS observations with a resolution of 250 m during the period of 2000–2022. The tree cover estimation was improved relative to conventional global tree cover mapping methods by developing highly discriminative input features and near global sampling training data. MODIS annual observations were realigned at the pixel level to eliminate phenological differences among regions. The realigned annual series were condensed into twelve features showing high separability between trees and herbaceous vegetation to reduce the dimension of features. A global covering training dataset, comprising 465.88 million sample points, was extracted across the globe through the aggregation and combination of forest/land cover maps from ESA WorldCover, GlobeLand30, PALSAR FNF, and ESRI Land Cover to improve the representativeness of training data. A feed-forward neural network was calibrated to predict fractional tree cover from MODIS data. The spatial pattern of the estimation results was generally consistent with the CGLS-LC100 product at global scale, with the average MAE in global vegetated areas of 12.50 %, while our dataset provided extended temporal coverage. The interannual stability of the estimated tree cover series was improved compared to MODIS vegetation continuous fields products for deciduous broadleaf forests, evergreen broadleaf forests, and mixed forests, with the global average value of mean absolute deviation (MAD) in tree cover series reduced by 5.8 %, 46.9 %, and 18.3 %, respectively. The estimation results were assessed using globally distributed validation data around BELMANIP 2.1 sites and those derived from the USGS circa 2010 global land cover reference dataset, leading to the R values of 0.93 and 0.73, MAE of 4.24 % and 10.55 %, and RMSE of 11.45 % and 17.98 %, respectively. This dataset could enhance the capability to monitor forest cover changes, particularly gradual changes such as forest recovery.

中文翻译：

---

用于森林覆盖变化分析的全球树木覆盖率制图

树木覆盖率有助于利用卫星数据表征森林覆盖变化。然而，生成满足森林覆盖变化监测年际稳定性要求的树木覆盖率数据集仍然存在重大挑战。本研究根据2000-2022年期间分辨率为250 m的MODIS观测数据生成了全球年度树木覆盖率数据集，命名为GLOBMAP Fractional Tree Cover。通过开发高度辨别性的输入特征和近全局采样训练数据，相对于传统的全局树木覆盖映射方法，树木覆盖估计得到了改进。 MODIS 年度观测结果在像素级别进行了重新调整，以消除区域之间的物候差异。重新排列的年度序列被浓缩为十二个特征，显示树木和草本植被之间的高度可分离性，以减少特征的维度。通过对ESA WorldCover、GlobeLand30、PALSAR FNF、ESRI Land Cover等森林/土地覆盖图进行聚合组合，提取全球范围内46588万个样本点的覆盖训练数据集，提高训练数据的代表性。校准前馈神经网络以根据 MODIS 数据预测树木覆盖率。估计结果的空间格局与全球范围内的CGLS-LC100产品基本一致，全球植被区域的平均MAE为12.50%，而我们的数据集提供了扩展的时间覆盖范围。与落叶阔叶林、常绿阔叶林和混交林的MODIS植被连续田产品相比，估计的树木覆盖系列的年际稳定性有所提高，树木覆盖系列的平均绝对偏差（MAD）全球平均值降低了5.8分别为 %、46.9% 和 18.3%。使用 BELMANIP 2.1 站点周围的全球分布式验证数据以及来自 USGS 大约 2010 年全球土地覆盖参考数据集的数据对估计结果进行评估，得出 R 值为 0.93 和 0.73，MAE 为 4.24% 和 10.55%，RMSE 为 11.45分别为 % 和 17.98%。该数据集可以增强监测森林覆盖变化的能力，特别是森林恢复等渐进变化。