Land-based macroplastic is considered one of the major sources of marine plastic debris. However, estimations of plastic emission from rivers into the oceans remain scarce and uncertain, mainly due to a severe lack of standardized observations. To properly assess global plastic fluxes, detailed information on spatiotemporal variation in river plastic quantities and composition are urgently needed. In this paper, we present a new methodology to characterize riverine macroplastic dynamics. The proposed methodology was applied to estimate the plastic emission from the Saigon River, Vietnam. During a 2-week period, hourly cross-sectional profiles of plastic transport were made across the river width. Simultaneously, sub-hourly samples were taken to determine the weight, size and composition of riverine macroplastics (>5 cm). Finally, extrapolation of the observations based on available hydrological data yielded new estimates of daily, monthly and annual macroplastic emission into the ocean. Our results suggest that plastic emissions from the Saigon River are up to four times higher than previously estimated. Importantly, our flexible methodology can be adapted to local hydrological circumstances and data availability, thus enabling a consistent characterization of macroplastic dynamics in rivers worldwide. Such data will provide crucial knowledge for the optimization of future mediation and recycling efforts.

Plastic pollution in aquatic environments is an increasing global risk. In recent years, marine plastic pollution has been studied to a great extent, and it has been hypothesized that land-based plastics are its main source. Global modeling efforts have suggested that rivers in South East Asia are in fact the main contributors to plastic transport from land to the oceans. However, due to a lack of plastic transport observations, the origin and fate of riverine plastic waste is yet unclear. Here, we present results from a first assessment of riverine macroplastic emission from rivers and canals that run through a densely populated coastal urban city. Using a combination of field measurements, empirical relations and hydraulic modeling, we provide an estimate of total riverine plastic export originating from Jakarta, Indonesia, into the ocean. Furthermore, we provide insights in its composition, and variation in time and space. We found that most macroplastics in Jakarta consists of films and foils. We estimate that 2.1 × 10 3 tonnes of plastic waste, is transported from land to sea annually, equaling 3% of the total annual unsoundly disposed plastic waste in the Jakarta area.

Quantifying plastic pollution on surface water is essential to understand and mitigate the impact of plastic pollution to the environment. Current monitoring methods such as visual counting are labor intensive. This limits the feasibility of scaling to long‐term monitoring at multiple locations. We present an automated method for monitoring plastic pollution that overcomes this limitation. Floating macroplastics are detected from images of the water surface using deep learning. We perform an experimental evaluation of our method using images from bridge‐mounted cameras at five different river locations across Jakarta, Indonesia. The four main results of the experimental evaluation are as follows. First, we realize a method that obtains a reliable estimate of plastic density (68.7% precision). Our monitoring method successfully distinguishes plastics from environmental elements, such as water surface reflection and organic waste. Second, when trained on one location, the method generalizes well to new locations with relatively similar conditions without retraining (≈50% average precision). Third, generalization to new locations with considerably different conditions can be boosted by retraining on only 50 objects of the new location (improving precision from ≈20% to ≈42%). Fourth, our method matches visual counting methods and detects ≈35% more plastics, even more so during periods of plastic transport rates of above 10 items per meter per minute. Taken together, these results demonstrate that our method is a promising way of monitoring plastic pollution. By extending the variety of the data set the monitoring method can be readily applied at a larger scale.