LABPLAS Plastic Debris Classified Satellite Images for Honduras (2019-2024)

Here you find the satellite-derived maps (PNGs) of predicted locations of floating macroplastic aggregations between 2019 and 2024, in the coastal region of the Motagua River plume (Honduras), developed under the H2020 LABPLAS project. The maps are classified using the POS2IDON tool and two specific machine learning models (the UNET and XGBOOST models) and the true-color (RGB) images. The predicted locations of floating macroplastic aggregations are marked with large red dots in the classified maps.

The classification maps were created with POS2IDON pipeline, a tool to detect suspected locations of floating marine debris in Sentinel- 2 satellite imagery using machine learning. POS2IDON includes modules for data acquisition, pre-processing, and pixel-based classification using different machine learning models (e.g. Random Forest, XGBoost, Unet). The outputs of POS2IDON include classification maps for all the available Sentinel-2 imagery of a given region of interest and temporal period, specified by the user.

Using POS2IDON we performed a long-term analysis in the region of the Motagua River plume (Honduras), which is infamous for its plastic pollution, largely due to substantial riverine inputs of plastic from Motagua river. This river is known for its "trash tsunamis" and the OceanCleanUp has installed the “Interceptor Barricade” in an upstream location. Long-term synoptic assessments of plastic pollution are the primary goal, and the Honduras Gulf represents an outstanding example of a region to test methods. Confidence in results can be taken especially in the Honduras Gulf region since it is known for recurrent and large aggregations of floating plastics in the coastal ocean, and where the models are trained.

POS2IDON was applied in the Sentinel-2 archive between 2019 and 2024. After running POS2IDON, classification images (for UNET and XGBOOST models) were obtained. Subsequently, to decrease the number of potential false positives, automated post-processing procedures were applied, including the buffering of the clouds (from cloud mask and cloud class) and the removal of isolated MD pixels. This resulted in a total of 438 classified & post-processed images (i.e. 1 image every ~5 days), which were then used for long-term analysis, and provided in this dataset.