Sustainable Apparel Supply Chains: A Review of AI-Driven Optimization, Waste Reduction, and Circular Economy Practices

Circular Logistics Engineering: Minimizing Waste and Carbon Footprint

The shift from linear to circular economic systems has created new needs for the design of logistics systems, especially for minimising waste and reducing the carbon footprint. This review discusses how logistics engineering can incorporate the principles of a circular economy to support the realisation of more resource-efficient, low-carbon, and recovery-oriented supply systems. The article begins by elucidating the theoretical principles of circular logistics by contrasting it with traditional, green, reverse, and closed-loop logistics, and by emphasising the necessity of considering logistics as a multi-directional system to retain value rather than distributing products in a one-way manner. It subsequently develops key engineering advances, including sustainable transport, smart warehousing, reverse logistics infrastructure, reusable packaging, and digital technologies such as IoT, AI, and digital twins. The review also examines the optimisation models and decision-support strategies applied to balance cost, service, and waste reduction and carbon mitigation under uncertainty. Moreover, it assesses the barriers to implementation in terms of infrastructure, economics, organisational capacity, regulation and sector-specific conditions of operation. The article posits that the originality of logistics driven by the circular economy lies in its comprehensive approach to waste and carbon goals through engineering design, rather than distinct green interventions. The review concludes that the idea of circular logistics can become a vital facilitator of sustainable industrial change, but it will require the assistance of lifecycle-based assessment, integrated infrastructure, and context-specific implementation strategies.

AI-DRIVEN SUPPLY CHAIN OPTIMIZATION FOR SUSTAINABILITY: EVIDENCE FROM NIGERIA MANUFACTURING INDUSTRY

The growing demand for sustainability in manufacturing and the inefficiencies of traditional methods in the supply chain highlight the importance of finding smarter solutions. Even with the growing availability of digital tools and AI technologies, organizations are yet to fully utilize them to aid sustainability efforts, causing inefficient use of resources, waste, and environmental damage. The chapter examined AI supply chains optimizing for sustainability: evidence from Nigeria manufacturing industry.  The chapter utilized a survey research design with a population of 950 supply chain employees in Nigerian Breweries, Lagos State, with an estimated sample size of 281 using the Yamane (1967) formula. Data was collected using a structured questionnaire with a five-point Likert scale. Descriptive statistics and multiple regression analysis were used to analyze the data in SPSS version 27. The findings showed that AI-driven demand forecasting (coefficient = 4.287) and AI-based inventory optimization (coefficient = 3.549) have a positive significant on sustainability, with 56.7% of the variance in sustainability outcomes. The chapter concluded that AI-driven supply chain optimization plays a significant role in minimizing waste, optimizing resources, and meeting market demand.  The study recommended that Nigerian Breweries should utilize AI-powered demand forecasting tools for production planning and should implement AI-based inventory optimization systems to ensure that inventory levels are optimized and reducing excess stock.

A Comparative Study of Extended Inventory Management in Two-Warehouse System

Modern inventory management, environmental concerns, and supply chain management challenges have made the two-warehouse system a necessary and strategic approach. Early studies explored demand patterns, this system increases flexibility, reduces risk, and improves efficiency, while also facilitating the implementation of modern strategies such as green sustainability practices, the use of renewable resources, preservation technologies, and carbon-efficient supply chain management. Studies began with exploring demand patterns, backlogging, LIFO and FIFO dispatching systems, trade credit financing, and various modelling methods related to product deterioration over time. More recent research has incorporated factors aimed at improving ecological performance, such as reverse logistics, carbon emission control, sustainable transportation, preservation methods, and green technologies. This review paper emphasizes the urgent need to optimize sustainable two-warehouse inventory models within an economically beneficial, sustainable, smart, and climate-resilient framework, and to integrate preservation and green technologies, carbon emission regulations, and multi-echelon supply chain frameworks into future research and practice.

A collaborative framework for zero waste and circular supply chains solution in the circular economy

A SUSTAINABLE MANUFACTURING OPTIMIZATION MODEL FOR IMPERFECT PRODUCTION UNDER CIRCULAR ECONOMY, INFLATION, AND CARBON EMISSION

This study proposes an integrated optimization framework for a sustainable supply chain. It emphasizes circular economy practices and the convergence of carbon emissions regulation. While improving economic efficiency within the footwear industry. This study presents a waste free sustainable supply chain model with a single manufacturer and a single retailer, where the production is not completely perfect. Supply chain management and sustainable business models are closely linked in that the structure of supply networks can influence the concept of the development of the sustainable business model and vice versa. The purpose of this study is to optimize the entire supply chain while encouraging economic feasibility and environmental sustainability.The manufacturer’s process could be improved at converting resources into useful products. Hence, some faulty products are produced during production, which is a different waste. To handle this kind of waste, refurbished the quantity and sold it in the market. The machine wastes some raw material in trimming, grinding, and refining. Keeping the circular economy concept, this collected waste is recycled and reused as a raw material for manufacturing. This study offers a framework for developing a supply chain network that applies circular principles while accounting for inflation to reduce waste. It proposes a method for sustainably producing substances that involves cooperation between manufacturers and stores. The research aims to reduce overall costs through an analytical approach. The sensitivity analysis additionally examines the model’s stability, demonstrating that it is relatively stable. This study examines the use of recycled scrap as a raw material, which has a modest impact on the total production cost.

AI-Driven Supply Chains: Enhancing Efficiency and Sustainability in Modern Commerce

The use of AI is transforming supply chain management, moving from a reactive to a proactive, adaptive, and data-driven approach. This research explores the impact of AI in the supply chain on enhancing operational efficiency and fostering sustainability in today's business landscape. The focus of the research is in the application of machine learning, predictive analysis, smart automation, Internet of Things (IoT) connected systems, demand forecasting, inventory optimization, route planning and real-time tracking of the supply chain network. AI can help with more accurate demand forecasting, curbing overstocking, transportation inefficiencies, optimizing resource usage and enhancing responsiveness to market changes. Concurrently, AI-powered supply chain systems can play a role in sustainability by minimizing material waste, optimizing energy usage, curbing unnecessary transportation, and promoting smart utilization of natural resources. The benefits of AI are also reliant on the quality of data, technology, organization, employee skills, cybersecurity, and responsible data management practices. Part particular special attention is given to the connection between technical efficiency and environmental concern – excessive dependence on computational technologies can create energy and resource problems. The paper, therefore, argues that AI is a strategic enabler, rather than a solution on its own to the problem of supply chain. A combination of intelligent technologies and sustainable business practices adds to the resilience of supply chains, improves economic outcomes and helps an organisation better meet evolving customer and environmental needs. In conclusion, the study highlights the potential of AI to revolutionize supply chain management practices, enabling businesses to build efficient, sustainable, resilient, and transparent supply chains.