Analysis and forecasting of national marine litter based on coastal data in South Korea from 2009 to 2021

• Published in: Marine pollution bulletin 2023-04, Vol.189, p.114803-114803, Article 114803
• Main Authors: Park, Min-Ho, Yeo, Siljung, Yang, Seung-Kwon, Shin, Donguk, Kim, Jeong-Hwan, Choi, Jae-Hyuk, Lee, Won-Ju
• Format: Article
• Language: English
• Subjects: Bathing Beaches; Environmental Monitoring; Forecasting; Marine litter; N-BEATS; N-HiTS; Neural Networks, Computer; Plastics - analysis; Republic of Korea; Seasons; Statistical analysis; Time Factors; Waste Products - analysis
• ISSN: 0025-326X; 1879-3363
• DOI: 10.1016/j.marpolbul.2023.114803

In this study, statistical analysis and forecasting were performed using coastal litter data of Korea. The analysis indicated that rope and vinyl accounted for the highest proportion of coastal litter items. The statistical analysis of the national coastal litter trends revealed that the greatest concentration of litter was observed during summer months (June–August). To predict the amount of coastal litter per meter, recurrent neural network (RNN)-based models were used. Neural basis expansion analysis for interpretable time series forecasting (N-BEATS) and neural hierarchical interpolation for time series forecasting (N-HiTS), an improved model of N-BEATS recently announced, were used for comparison with RNN-based models. When predictive performance and trend followability were evaluated, overall N-BEATS and N-HiTS outperformed RNN-based models. Furthermore, we found that average of N-BEATS and N-HiTS models yielded better results than using one model. [Display omitted] •Marine litter data for 13 years from 19 coastal areas in Korea were collected.•The analysis revealed that the south coast had an abundant average, largely comprising rope and vinyl.•N-BEATS and N-HiTS showed better performance than RNN-based models to predict marine litter.•The predictive performance of the average of N-BEATS and N-HiTS was superior to that of each model.