AIPOWERED CARBON FOOTPRINT PREDICTION OPTIMIZATION FOR SUSTAINABLE LOGISTICS USING MACHINE LEARNING AND GENERATIVE AI

Project Code :TCMAPY1932

Objective

The project aims to develop and deploy a Deeplearning learning based system hosted on Google Cloud Platform (GCP) to predict and optimize carbon emissions across the logistics supply chain including procurement, manufacturing, warehousing, and transportation. Using models like Random Forest, LSTM, XGBoost, and GRU, the system forecasts carbon footprints, identifies ESG risk hotspots, and provides generative AI–driven recommendations to reduce emissions. It features an intuitive, GCP-hosted interface with SHAP-based model transparency and AI summaries, enabling organizations to make data-driven, sustainable, and scalable decisions to minimize their environmental impact.

Abstract

The "AI-Powered Carbon Footprint Prediction Optimization for Sustainable Logistics Using Machine Learning and Generative AI" project aims to predict and optimize carbon emissions across various stages of the supply chain. By leveraging machine learning models such as Random Forest, LSTM, XGBoost, and GRU, the system provides accurate carbon footprint predictions. The project incorporates generative AI to generate summaries, provide actionable sustainability insights, and identify potential ESG risk hotspots. The dataset includes factors such as procurement, energy consumption, transportation modes, and external conditions like weather, which influence emissions. The platform, built with HTML, CSS, JavaScript, Python (Flask), and hosted on Google Cloud Platform (GCP), offers a user-friendly interface with modules like Home, Register, Login, Dashboard, and Logout. The dashboard displays predictions, SHAP plots, and ESG insights, assisting organizations in reducing their environmental impact. The system’s goal is to streamline decision-making and support sustainability by identifying areas for improvement in emissions management. The generative AI enhances the overall system by offering suggestions for optimizing operations, reducing emissions, and improving supply chain sustainability.

Keywords: AI, Carbon Footprint, Machine Learning, Sustainability, ESG, Emissions Prediction, Generative AI, Supply Chain, Optimization, Random Forest, LSTM, XGBoost, GRU, Flask.

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.