Plastic waste and its environmental hazards have been attracting public attention as a global sustainability issue. This study builds a neural network model to forecast plastic waste generation of the EU-27 in 2030 and evaluates how the interventions could mitigate the adverse impact of plastic waste on the environment. The black-box model is interpreted using SHapley Additive exPlanations (SHAP) for managerial insights. The dependence on predictors (i.e., energy consumption, circular material use rate, economic complexity index, population, and real gross domestic product) and their interactions are discussed. The projected plastic waste generation of the EU-27 is estimated to reach 17 Mt/y in 2030. With an EU targeted recycling rate (55%) in 2030, the environmental impacts would still be higher than in 2018, especially global warming potential and plastic marine pollution. This result highlights the importance of plastic waste reduction, especially for the clustering algorithm-based grouped countries with a high amount of untreated plastic waste per capita. Compared to the other assessed scenarios, Scenario 4 with waste reduction (50% recycling, 47.6% energy recovery, 2.4% landfill) shows the lowest impact in acidification, eutrophication, marine aquatic toxicity, plastic marine pollution, and abiotic depletion. However, the global warming potential (8.78 Gt CO₂eq) is higher than that in 2018, while Scenario 3 (55% recycling, 42.6% energy recovery, 2.4% landfill) is better in this aspect than Scenario 4. This comprehensive analysis provides pertinent insights into policy interventions towards environmental hazard mitigation.

塑料废物及其对环境的危害已作为全球可持续发展问题引起了公众的关注。本研究建立了一个神经网络模型来预测 2030 年欧盟 27 国的塑料废物产生量，并评估干预措施如何减轻塑料废物对环境的不利影响。使用 SHapley Additive exPlanations (SHAP) 解释黑盒模型以获得管理洞察力。讨论了对预测变量（即能源消耗、循环材料使用率、经济复杂性指数、人口和实际国内生产总值）的依赖性及其相互作用。预计到 2030 年，欧盟 27 国的塑料废物产生量预计将达到 17 吨/年。按照欧盟 2030 年的目标回收率（55%），环境影响仍将高于 2018 年，尤其是全球变暖潜能值和塑料海洋污染。这一结果凸显了减少塑料垃圾的重要性，特别是对于人均未处理塑料垃圾数量较多的基于聚类算法的分组国家。与其他评估情景相比，减少废物的情景 4（50% 回收利用，47.6% 能源回收，2.4% 填埋）在酸化、富营养化、海洋水生毒性、塑料海洋污染和非生物耗竭方面的影响最小。然而，全球变暖潜能值（8.78 Gt CO 减少废物的情景 4（50% 的回收利用，47.6% 的能源回收，2.4% 的垃圾填埋场）显示出对酸化、富营养化、海洋水生毒性、塑料海洋污染和非生物耗竭的影响最小。然而，全球变暖潜能值（8.78 Gt CO 减少废物的情景 4（50% 的回收利用，47.6% 的能源回收，2.4% 的垃圾填埋场）显示出对酸化、富营养化、海洋水生毒性、塑料海洋污染和非生物耗竭的影响最小。然而，全球变暖潜能值（8.78 Gt CO₂ eq) 高于 2018 年，而情景 3（55% 的回收利用，42.6% 的能源回收，2.4% 的垃圾填埋场）在这方面优于情景 4。这一综合分析为缓解环境危害的政策干预提供了中肯的见解。