Remote sensing applications are garnering much attention as a promising solution for detection, tracking and monitoring of floating marine litter (FML). With an increasing number of studies portraying the technical feasibility of FML detection, we attempt here to experimentally observe a minimum detectable abundance fraction of floating plastic (white HDPE sheets), in a Sentinel-2 and PlanetScope SuperDove pixel. Such a threshold can set a baseline for detectability in terms of pixel-based spectral classification methodologies, and can be especially relevant for low-FML-concentration areas such as the Northeastern Mediterranean. We constructed and deployed artificial targets comprising of 1, 2 and 3 m2 of floating white HDPE sheets. We acquired Sentinel-2 and SuperDove data of the target deployment area, along with ancillary data which assists with imagery interpretation. The data is atmospherically corrected (ACOLITE v.20221114) and a spectral separability analysis is performed using the spectral angle distance metric, to assess the possibility of spectrally discriminating the FML targets from water pixels in the scene. Results show that the detection threshold is above 3 m2 for the Sentinel-2 satellite, while the SuperDove’s higher spatial resolution results in spectral angles between the FML targets and water pixels in the scene which show marginal separability for the 2 and 3 m2 HDPE targets. When applying a partial unmixing detection algorithm using a previously acquired signature, we could detect the 3 m2 target in both the Sentinel-2 and SuperDove images, but with commission errors that render the feasibility of practical application of such low FML concentrations detection questionable.

中文翻译：

---

Sentinel-2 和 Planet Super Dove 图像中勉强可探测的漂浮塑料目标的实验观测


遥感应用作为检测、跟踪和监测漂浮海洋垃圾 （FML） 的有前途的解决方案而备受关注。随着越来越多的研究描绘了 FML 检测的技术可行性，我们在这里尝试在 Sentinel-2 和 PlanetScope SuperDove 像素中实验观察到漂浮塑料（白色 HDPE 片材）的最小可检测丰度分数。这样的阈值可以根据基于像素的光谱分类方法为可检测性设定基线，并且对于 FML 浓度低的区域（如地中海东北部）尤其相关。我们建造并部署了由 1、2 和 3 m2 漂浮的白色 HDPE 板组成的人工目标。我们获取了目标部署区域的 Sentinel-2 和 SuperDove 数据，以及有助于图像解释的辅助数据。对数据进行大气校正 （ACOLITE v.20221114），并使用光谱角度距离度量进行光谱可分离性分析，以评估在光谱上区分 FML 目标与场景中水像素的可能性。结果表明，Sentinel-2 卫星的检测阈值高于 3 m2，而 SuperDove 较高的空间分辨率导致 FML 目标与场景中的水像素之间的光谱角显示 2 和 3 m2 HDPE 目标的边际可分性。当使用先前获取的签名应用部分解混检测算法时，我们可以在 Sentinel-2 和 SuperDove 图像中检测到 3 m2 目标，但存在调试误差，这使得这种低 FML 浓度检测的实际应用可行性值得怀疑。