A novel beach litter analysis system based on UAV images and Convolutional Neural Networks

A novel deep learning-based floating garbage detection approach and its effectiveness evaluation in environmentally sustainable development

Floating garbage removal is an essential environmental strategy to reduce water pollution and achieve environmental sustainability, and it is a pressing issue for global ecological restoration. Under the interference of complex environments, floating garbage will gather, overlap, and change its shape due to water flow and wind. Efficient and automatic detection and collection of floating garbage gathered on the water surface is a challenging environmental management task. This study proposed an efficient and economical deep learning solution based on YOLOv8 (You Only Look Once v8). By improving the backbone, introducing the Wise-Powerful IoU loss, and adding the AuxHead detection head, the negative impact of complex environmental factors was effectively compressed, and the detection mean Average Precision(mAP) of the surface model aggregated floating garbage was improved to 89.4 %. The Precision(P) was improved to 95.8 %. The model size is only 18.8 MB, and the number of model parameters is reduced by 32.2 % compared with the original model. The proposed model addresses the challenging issue of detecting aggregated floating garbage on the water surface, and the lightweight model is also more conducive to promoting outdoor use. The research results can improve the aggregated floating garbage collection rate by up to 61.5 % compared with the mainstream model Faster R-CNN. It can save up to about 1730.3 kW·h of electricity per ton of recycled waste oil and reduce the emission of 452.7 kg of CO2 and 2328.8t of water pollution. The scheme is superior to the current technical level in terms of detection Precision and mean Average Precision and makes essential scientific contributions to the protection and restoration of water ecosystems, energy conservation, emission reduction, and carbon reduction.

Indoor laboratory experiments for beach litter spectroradiometric analyses

Marine pollution is a growing global issue, impacting both marine ecosystem and human health. High quantities of debris, mainly composed by plastic items, have been identified both in the coastal area and in the sea environment. Remote sensing techniques represent an useful tool (complementary to the in-situ campaigns) to monitor litter in the coastal environment, especially if the spectral signatures of the debris are known. In this framework, harvested beach litter (plastic items especially) were collected from two sandy beaches. The samples were spectrally characterised by implementing two indoor laboratory experiments with the aim to infer the best wavelengths to be used for beach litter detection via the spectral angle mapper index. Due to lack of a scientific protocol concerning the spectral data acquisition, two experimental setups were carried out to simulate the direct and diffuse illumination conditions. For around 30% of the samples, the spectral signatures are influenced by the two experimental setups. Outcomes suggest that for the majority of the samples green, blue, red-edge and some infrared bands are suitable for the beach litter detection.

Application of improved machine learning in large-scale investigation of plastic waste distribution in tourism Intensive artificial coastlines

Oceans are ultimately a sink of plastic waste. Complex artificial coastlines pose remarkable challenges for coastal plastic waste monitoring. With the development of machine learning methods, high detection accuracy can be achieved; however, many false positives have been noted in various network models used for plastic waste investigation. In this study, extensive surveys of artificial coastlines were conducted using drones along the Dongjiang Port artificial coastline in the Binhai District, Tianjin, China. The deep learning model YOLOv8 was enhanced by integrating the InceptionNeXt and LSK modules into the network to improve its detection accuracy for plastic waste and reduce instances of tourists being misidentified as plastic. In total, 553 high-resolution coastline images with 3488 items of detected plastic waste were compared using the original and improved YOLOv8 models. The improved YOLOv8s-IL model achieved a detection rate of 64.9%, a notable increase of 11.5% compared with that of the original model. The number of false positives in the improved YOLOv8s-IL model was reduced to 32.3%, the multi-class F-score reached 76.5%, and the average detection time per image was only 2.7 s. The findings of this study provide technical support for future large-scale monitoring of plastic waste on artificial coastlines.

A set of guidelines as support for the integrated geo-environmental characterization of highly contaminated coastal sites

The knowledge of geomorphodynamic aspects is crucial for understanding marine and coastal processes/dynamics as well as for characterizing coastal environments heavily affected by anthropogenic activities. To provide a framework of analysis that can be applied in a consistent way for the geo-environmental characterization of highly contaminated coastal sites, in this paper a set of operational guidelines is proposed. Special attention is given to the role of geomorphological-based surveys and analyses in defining (i) the site-specific geological model of the investigated site, (ii) the anthropogenic impacts on marine and coastal sediments, (iii) the expected morphodynamic variations induced by climate change and anthropogenic interventions, (iv) tailored dissemination activities and community engagement plans. Then, an evaluation of the state of the art of activities already performed for the characterization of the coastal contaminated sites located in the Apulia region (southern Italy) is provided. The outcomes of this research are also provided in the form of infographics to favor their dissemination among communities and stakeholders.

Machine learning to support citizen science in urban environmental management

Machine learning (ML) and citizen science (CS) are increasingly prevalent and rapidly evolving approaches to studying and managing environmental challenges. Municipal and other governance actors can benefit from technology advances in ML and public engagement benefits of CS but must also address validity and other quality assurance concerns in their application to particular management contexts. In this article, we take up the pervasive challenge of urban litter to demonstrate how ML can support CS by providing quality assurance in the regulatory context of California's stormwater program. We gave quantitative CS-collected data to five ML models to compare their predictions of a qualitative, site-specific, multiclass "Litter Index" score, an important regulatory metric typically only assessed by trained experts. XGBoost had the best outcome, with scores of 0.98 for accuracy, precision, recall and F-1. These strong results show that ML can provide a reliable complement to CS assessments and increase quality assurance in a regulatory context. To date, ML and CS have each contributed to litter management in novel ways and we find that their integration can provide important synergies with additional applications in other environmental management domains.

The nauticAttiva project: A mobile phone-based tool for the citizen science plastic monitoring in the marine and coastal environment

Plastic pollution is involving large coastal areas of the Mediterranean Sea. Innovative methods of plastic monitoring can be addressed through the citizen science approaches integrated with mobile phones. On the other hand, the availability of mobile phones is increasing among several users. Mobile phones can be integrated with a web mobile app, which allows to collect a lot of data for extended areas and in a short temporal range. In this study, the web service of iNaturalist was applied to implement a mobile phone-based tool to collect pictures of plastic items. At present, the web mobile app has been used to collect pictures of plastic debris in the Mediterranean Sea. Results were compared with the Mediterranean hydrodynamic regime, to highlight the pathways and densities of the plastic items. The proposed mobile phone-based tool represented a citizen science approach useful for the acquisition of plastic observations in the marine and coastal environment.