Published Paper Details:

Carbon Footprint Optimization Optimize AI-powered Carbon footprint prediction for Sustainable Logistics is a project that is expected to predict and optimize the carbon emission at different points in the supply chain. The system measures carbon footprint using machine learning models including the Random Forest, LSTM and XGBoost, and GRU applications that offer precise predictions of carbon footprint. In the project, generative AI is integrated to produce summaries, offer actionable sustainability information, and possible ESG risk hotspots. The dataset captures the factors like procurement, energy usage, modes of transportation and external factors like weather, which contribute towards the emissions. It is an HTML, CSS, JavaScript, Python (Flask), and hosted on Google Cloud Platform (GCP) platform which provides an easy to use interface with modules such as Home, Register, Login, dashboard and Logout. Some of the dashboard features include predictions, SHAP plot, and ESG insights, which help organizations to reduce the environmental impact. This system is aimed at facilitating the decision-making process and ensuring sustainability through areas of the improvement of emissions management. The suggested generative AI will complement the entire system with proposals on how to streamline the workings of the system, minimize emissions, and increase the sustainability of the supply chain.