本研究證實AI Slop內容生成雖具有便利性與低成本特性，但其背後仍伴隨能源消耗及環境負荷。未來研究可進一步納入不同AI模型、資料中心區域配置及設備生命週期等因素，以提升人工智慧環境衝擊評估之完整性與準確性。;In recent years， the rapid advancement of Generative Artificial Intelligence (Generative AI) has significantly accelerated the development of automated content creation， including text， images， audio， and videos. Among these applications， a phenomenon known as “AI Slop” has emerged， referring to large quantities of low-quality， repetitive， and automatically generated content. The generation of AI-based video content relies heavily on high-performance Graphics Processing Units (GPUs)， large-scale data centers， and cooling systems， resulting in considerable energy consumption， water usage， and greenhouse gas emissions. However， existing studies have primarily focused on the technical performance and commercial applications of AI， while limited attention has been paid to the environmental impacts associated with AI-generated content， particularly AI Slop videos. This study applies the Life Cycle Assessment (LCA) methodology to evaluate the energy consumption and environmental impacts of AI Slop video generation. A 30-second AI Slop video was defined as the functional unit (FU). The system boundary includes upstream energy supply， core processes involving AI model inference and data center operations， as well as downstream data transmission and content distribution. Life Cycle Inventory (LCI) data were compiled from publicly available literature， industry reports， and environmental databases. Environmental impacts were assessed using LCA software， including Global Warming Potential (GWP)， energy consumption， water use， and other environmental impact indicators. Sensitivity analysis and uncertainty analysis were further conducted to evaluate the robustness of the assessment results. The results indicate that the environmental impacts of AI Slop video generation are primarily associated with AI model inference and data center operations. GPU computation and cooling systems were identified as the major environmental hotspots. Although the environmental burden of a single AI-generated video is relatively limited， the cumulative impacts could become significant due to the large-scale generation and dissemination of AI content. In addition， factors such as electricity generation mix， data center energy efficiency， and AI model complexity were found to substantially influence the overall environmental performance. This study establishes a quantitative assessment framework for evaluating the environmental impacts of AI Slop video generation and provides a foundation for future research on sustainable AI development. The findings may serve as a reference for AI service providers， data center operators， and policymakers in developing energy management strategies， carbon disclosure mechanisms， and sustainability-related policies， thereby promoting a balance between technological innovation and environmental sustainability.
