Pollution in the form of litter in the natural environment is one of the great challenges of our times. Automated litter detection can help assess waste occurrences in the environment. Different machine learning solutions have been explored to develop litter detection tools, thereby supporting research, citizen science, and volunteer clean-up initiatives. However, to the best of our knowledge, no work has investigated the performance of state-of-the-art deep learning object detection approaches in the context of litter detection. In particular, no studies have focused on the assessment of those methods aiming their use in devices with low processing capabilities, e.g., mobile phones, typically employed in citizen science activities. In this paper, we fill this literature gap. We performed a comparative study involving state-of-the-art CNN architectures (e.g., Faster RCNN, Mask-RCNN, EfficientDet, RetinaNet and YOLO-v5), two litter image datasets and a smartphone. We also introduce a new dataset for litter detection, named PlastOPol, composed of 2418 images and 5300 annotations. The experimental results demonstrate that object detectors based on the YOLO family are promising for the construction of litter detection solutions, with superior performance in terms of detection accuracy, processing time, and memory footprint.
Salmon lice are a severe problem in salmonid aquaculture and also affect wild salmon smolts migrating through fjord systems in spring. To keep the lice burden within acceptable limits, frequent use of chemical delousing has resulted in the parasite becoming resistant to these treatments. Alternative thermal and mechanical delousing practices induce welfare problems and loss of farmed fish. To avoid losing the constant arms race with the parasite, we need a new approach to the problem. Inspired by the natural host-parasite balance, we propose a change in salmonid aquaculture practices by combining and improving existing management strategies for a more holistic and sustainable vision of the industry. Before salmonids were farmed in open cages, few hosts were available for salmon lice during winter, which reduced the salmon lice populations to a minimum when the wild smolts were migrating to sea. Thus, the natural strategy is to decrease host availability for a sufficient period of time to allow salmon lice nauplii to die of starvation. Due to the long survival and drift of the nauplii, it is important to significantly increase the distance between open farming units, either by organising and aggregating farms in extensive fallowing areas with significant distance to other corresponding areas or by controlling water flow through active production units during extensive fallowing. Here we primarily address environmental interactions. Economic and juridical implications of the proposed strategy are not discussed in detail. However, we do briefly suggest relevant current regulations and possible costs and benefits of reducing delousing treatment intensity.
The issue of plastic pollution is recognised as a pervasive and ubiquitous problem which can pose a threat to ecosystems worldwide and potentially affect human health. In this perspective, we selected the latest research that identifies potential impacts beyond individual species to draw attention on wider biogeochemical cycles and the most fundamental biological processes we all depend on, namely, breathing, feeding and carrying offspring. We highlight the need for uniform research methods, giving examples of protocols and indicator species that should be evaluated by the research community for their potential wide adoption. We stress the need for systemic changes and our role as scientific community to demand changes proportionate to the severity and implications of our findings. We further explore the push and pull mechanisms between researchers and policymakers in relation to the global environmental challenges such as plastic pollution. Finally, we recommend a path of action inspired by the global action taken to address the ozone layer depletion by banning chlorofluorocarbons (CFC).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.