While at least 8 million tons of plastic litter are ending up in our oceans every year and research on marine litter detection is increasing, the spectral properties of wet as well as submerged plastics in natural marine environments are still largely unknown. Scientific evidence-based knowledge about these spectral characteristics has relevance especially to the research and development of future remote sensing technologies for plastic litter detection. In an effort to bridge this gap, we present one of the first studies about the hyperspectral reflectances of virgin and naturally weathered plastics submerged in water at varying suspended sediment concentrations and depth. We also conducted further analyses on the different polymer types such as Polyethylene terephthalate (PET), Polypropylene (PP), Polyester (PEST) and Low-density polyethylene (PE-LD) to better understand the effect of water absorption on their spectral reflectance. Results show the importance of using spectral wavebands in both the visible and shortwave infrared (SWIR) spectrum for litter detection, especially when plastics are wet or slightly submerged which is often the case in natural aquatic environments. Finally, we demonstrate in an example how to use the open access data set driven from this research as a reference for the development of marine litter detection algorithms.

The occurrence of litter in natural areas is nowadays one of the major environmental challenges. The uncontrolled dumping of solid waste in nature not only threatens wildlife on land and in water, but also constitutes a serious threat to human health. The detection and monitoring of areas affected by litter pollution is thus of utmost importance, as it allows for the cleaning of these areas and guides public authorities in defining mitigation measures. Among the methods used to spot littered areas, aerial surveillance stands out as a valuable alternative as it allows for the detection of relatively small such regions while covering a relatively large area in a short timeframe. In this study, remotely piloted aircraft systems equipped with multispectral cameras are deployed over littered areas with the ultimate goal of obtaining classification maps based on spectral characteristics. Our approach employs classification algorithms based on random forest approaches in order to distinguish between four classes of natural land cover types and five litter classes. The obtained results show that the detection of various litter types is feasible in the proposed scenario and the employed machine learning algorithms achieve accuracies superior to 85% for all classes in test data. The study further explores sources of errors, the effect of spatial resolution on the retrieved maps and the applicability of the designed algorithm to floating litter detection.