Uhl Johannes H, Leyk Stefan
University of Colorado Boulder, Institute of Behavioral Science, 483 UCB, Boulder, CO 80309, USA.
University of Colorado Boulder, Cooperative Institute for Research in Environmental Sciences (CIRES), 216 UCB, Boulder, CO 80309, USA.
Int J Appl Earth Obs Geoinf. 2023 Sep;123. doi: 10.1016/j.jag.2023.103469. Epub 2023 Aug 28.
Geospatial datasets derived from remote sensing data by means of machine learning methods are often based on probabilistic outputs of abstract nature, which are difficult to translate into interpretable measures. For example, the Global Human Settlement Layer GHS-BUILT-S2 product reports the probability of the presence of built-up areas in 2018 in a global 10 m × 10 m grid. However, practitioners typically require interpretable measures such as binary surfaces indicating the presence or absence of built-up areas or estimates of sub-pixel built-up surface fractions. Herein, we assess the relationship between the built-up probability in GHS-BUILT-S2 and reference built-up surface fractions derived from a highly reliable reference database for several regions in the United States. Furthermore, we identify a binarization threshold using an agreement maximization method that creates binary built-up land data from these built-up probabilities. These binary surfaces are input to a spatially explicit, scale-sensitive accuracy assessment which includes the use of a novel, visual-analytical tool which we call focal precision-recall signature plots. Our analysis reveals that a threshold of 0.5 applied to GHS-BUILT-S2 maximizes the agreement with binarized built-up land data derived from the reference built-up area fraction. We find high levels of accuracy (i.e., county-level F-1 scores of almost 0.8 on average) in the derived built-up areas, and consistently high accuracy along the rural-urban gradient in our study area. These results reveal considerable accuracy improvements in human settlement models based on Sentinel-2 data and deep learning, as compared to earlier, Landsat-based versions of the Global Human Settlement Layer.
通过机器学习方法从遥感数据中获取的地理空间数据集通常基于抽象性质的概率输出，这些输出难以转化为可解释的度量。例如，全球人类住区层GHS-BUILT-S2产品报告了2018年全球10米×10米网格中建成区存在的概率。然而，从业者通常需要可解释的度量，如表明建成区存在或不存在的二元表面，或亚像素建成区表面分数的估计值。在此，我们评估了美国几个地区GHS-BUILT-S2中的建成概率与从高度可靠的参考数据库中得出的参考建成区表面分数之间的关系。此外，我们使用一种一致性最大化方法确定了一个二值化阈值，该方法根据这些建成概率创建二元建成土地数据。这些二元表面被输入到一个空间明确、尺度敏感的精度评估中，该评估包括使用一种新颖的视觉分析工具，我们称之为焦点精确召回特征图。我们的分析表明，应用于GHS-BUILT-S2的0.5阈值可使与从参考建成区分数得出的二元建成土地数据的一致性最大化。我们在得出的建成区中发现了较高的精度水平（即平均县级F-1分数几乎为0.8），并且在我们的研究区域内沿城乡梯度的精度始终很高。与早期基于陆地卫星的全球人类住区层版本相比，这些结果表明基于哨兵-2数据和深度学习的人类住区模型的精度有了显著提高。
