Identifying floating plastic marine debris using a deep learning approach
Estimating the volume of macro-plastics which dot the world’s oceans is one of the most pressing environmental concerns of our time. Prevailing methods for determining the amount of floating plastic debris, usually conducted manually, are time demanding and rather limited in coverage. With the aid of deep learning, herein, we propose a fast, scalable, and potentially cost-effective method for automatically identifying floating marine plastics. When trained on three categories of plastic marine litter, that is, bottles, buckets, and straws, the classifier was able to successfully recognize the preceding floating objects at a success rate of ≈ 86%. Apparently, the high level of accuracy and efficiency of the developed machine learning tool constitutes a leap towards unraveling the true scale of floating plastics.
KeywordsImage classification Convolutional Neural Networks Data processing Deep learning Marine debris Plastics Monitoring
K. K. acknowledges financial support from the Universitas Foundation, the A. G. Leventis Foundation, and the University of Nicosia. A. A.’s work is financially supported by the European Union’s Horizon 2020 research and innovation program under grant agreement No 739551 (KIOS CoE) and from the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.
- Eriksen M, Lebreton LCM, Carson HS, Thiel M, Moore CJ, Borerro JC, Galgani F, Ryan PG, Reisser J (2014) Plastic pollution in the world’s oceans: more than 5 trillion plastic pieces weighing over 250,000 tons afloat at sea. PLoS ONE 9:1–15Google Scholar
- González-Fernández D, Hanke G (2017) Toward a harmonized approach for monitoring of riverine floating macro litter inputs to the marine environment. Front Mar Sci 4Google Scholar
- Hastie TJ, Tibshirani RJ, Friedman JH (2013) The elements of statistical learning: data mining, inference, and prediction. Springer, New YorkGoogle Scholar
- Kylili K, Artusi A, Kyriakides I, Hadjistassou C (2018) Tracking and identifying floating marine debris, 6th International Marine Debris Conference, San Diego, California, USGoogle Scholar
- Lebreton L, Slat B, Ferrari F, Sainte-Rose B, Aitken J, Marthouse R, Hajbane S, Cunsolo S, Schwarz A, Levivier A, Noble K, Debeljak P, Maral H, Schoeneich-Argent R, Brambini R, Reisser J (2018) Evidence that the Great Pacific Garbage Patch is rapidly accumulating plastic. Sci Rep 8:4666CrossRefGoogle Scholar
- LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D., 1989. Handwritten digit recognition with a back-propagation network, Proceedings of the 2nd International Conference on Neural Information Processing Systems. MIT Press, pp. 396–404Google Scholar
- MSFD Technical Subgroup on Marine Litter (2013) Guidance on monitoring of marine litter in European seas. JRC83985, Joint Research Centre Scientific and Policy Reports, LuxembourgGoogle Scholar
- Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. ICLR 2015Google Scholar
- Sun, C., Shrivastava, A., Singh, S., Gupta, A., 2017. Revisiting Unreasonable Effectiveness of Data in Deep Learning Era, 2017 IEEE International Conference on Computer Vision (ICCV), pp. 843–852Google Scholar
- Woodall LC, Sanchez-Vidal A, Canals M, Paterson GLJ, Coppock R, Sleight V, Calafat A, Rogers AD, Narayanaswamy BE, Thompson RC (2014) The deep sea is a major sink for microplastic debris. R Soc Open Sci 1Google Scholar