Using machine learning and beach cleanup data to explain litter quantities along the Dutch North Sea coast

Abstract

Abstract. Coastlines potentially harbor a large part of litter entering the oceans such as plastic waste. The relative importance of the physical processes that influence the beaching of litter is still relatively unknown. Here, we investigate the beaching of litter by analyzing a data set of litter gathered along the Dutch North Sea coast during extensive beach cleanup efforts between the years 2014–2019. This data set is unique in the sense that data is gathered consistently over various years by many volunteers (a total of 14,000), on beaches which are quite similar in substrate (sandy). This makes the data set valuable to identify what environmental variables might play an important role in the beaching process, and to explore the variability of beach litter. We investigate this by fitting a random forest machine learning regression model to the observed litter concentrations. We find that especially tides play an important role, where an increasing tidal variability and tidal height lead to less litter found on beaches. Relatively straight and exposed coastlines appear to accumulate more litter. The regression model indicates that transport of litter through the marine environment is also important in explaining beach litter variability. By understanding what processes cause the accumulation of litter on the coast, recommendations can be given for more effective removal of litter from the marine environment. We estimate that 16,000–31,400 kilograms (95 % confidence interval) of litter are located on the 365 kilometers of Dutch North Sea coastline.

Detecting the most effective cleanup locations using network theory to reduce marine plastic debris: a case study in the Galapagos Marine Reserve

“…Code and data availability. Code and data used to conduct the experiment and to create all of the figures are available at https: //doi.org/10.24416/UU01-QVIGJM (Ypma et al, 2022).…”

“…Although observations for the validation of this parameterization are limited, analysis by Pawlowicz et al (2019) of a set of beached drifters in the Salish Sea showed that this parameterization provides reasonable estimates for the beaching location. The choice for the beaching timescale, however, is uncertain and so far, values of λ B = 1-100 d have been used (e.g., Kaandorp et al, 2020Kaandorp et al, , 2022Onink et al, 2021). It seems that mainly quantitative analyses such as mass budgets are sensitive to the choice of the beaching timescale, but that beaching patterns are qualitatively robust against the choice for λ B .…”

“…Marine plastic debris is abundant in the global ocean (Browne et al, 2015;Lebreton et al, 2019) and is likely to increase in the coming decades if waste-management systems across the globe do not improve (Lebreton and Andrady, 2019;Lau et al, 2020). Although the spatial distribution of plastic in the ocean is strongly heterogeneous (Law et al, 2010;Goldstein et al, 2013;Buhl-Mortensen and Buhl-Mortensen, 2017;Kaandorp et al, 2022), both model simulations and observations indicate that land-based mismanaged waste is trapped in coastal zones and that in particular positively buoyant plastic is most likely to be found on or near coastlines (e.g., Lebreton et al, 2019;Onink et al, 2021;Morales-Caselles et al, 2021). This implies that beach cleanups can be a highly effective mitigation measure to minimize the negative impact of plastic pollution on marine coastal ecosystems (e.g., Haarr et al, 2019;Kaandorp et al, 2022).…”

“…Although the spatial distribution of plastic in the ocean is strongly heterogeneous (Law et al, 2010;Goldstein et al, 2013;Buhl-Mortensen and Buhl-Mortensen, 2017;Kaandorp et al, 2022), both model simulations and observations indicate that land-based mismanaged waste is trapped in coastal zones and that in particular positively buoyant plastic is most likely to be found on or near coastlines (e.g., Lebreton et al, 2019;Onink et al, 2021;Morales-Caselles et al, 2021). This implies that beach cleanups can be a highly effective mitigation measure to minimize the negative impact of plastic pollution on marine coastal ecosystems (e.g., Haarr et al, 2019;Kaandorp et al, 2022). Furthermore, beaches are more accessible and cheaper to clean than the open ocean or the seabed and targeting specifically macroplastic items (> 0.5 cm) will prevent the formation on the shorelines of microplastic, which is more difficult to remove (e.g., Andrady, 2011;Ryan et al, 2020;Jones et al, 2021).…”

“…As beach cleanups often rely on the availability of professionals and willingness of volunteers, the location and timing of the cleanup activities do not always correspond with the location where cleanups would have most impact (Critchell S. L. Ypma et al: Connectivity of the Galapagos Islands et al, 2015;Nelms et al, 2017). Kaandorp et al (2022) explained litter quantities observed along the Dutch North Sea coast by combining a large data set from beach cleanups with hydrodynamic data and virtual particle pathways. Doing so, they were able to give recommendations for optimizing cleanup efforts in the Netherlands.…”