Data-driven analytics and modelling of circular supply chains for net zero manufacturing

Abstract

This study aims to explore the application of data-driven analytics and modelling, using Convolutional Neural Networks (CNN) and MATLAB, to develop circular supply chains that support net zero manufacturing. As industries face growing pressure to reduce their environmental impact, circular supply chains, which focus on resource reuse, waste reduction, and sustainable production, are becoming essential. By integrating CNN models for data analysis and optimization, this research enhances the ability to identify inefficiencies, forecast demand, and optimize resource flows, contributing to a reduction in carbon emissions. Key findings demonstrate that circular supply chain strategies, enhanced by CNN-driven analytics, significantly reduce carbon footprints in manufacturing processes. The application of CNN, executed in MATLAB, enables advanced pattern recognition for optimizing material reuse, predicting logistical demands, and improving lifecycle management. These data-driven insights result in lower emissions, cost savings, operational efficiencies, and enhanced supply chain resilience. The implications of these findings suggest a transformative impact on the manufacturing industry. By adopting CNN-based analytics powered through MATLAB for circular supply chains, companies can achieve net zero goals while improving competitiveness. This approach fosters a shift towards sustainable manufacturing by minimizing reliance on finite resources and reducing waste, aligning the industry with global sustainability objectives.