CarbonLens AI- powered footprint tracker
Climate change and environmental sustainability have become major global concerns, highlighting the need for accessible tools that help individuals understand and reduce their carbon emissions. This paper presents CarbonLens, an AI-powered carbon footprint tracking and sustainability analytics platform designed to monitor personal carbon emissions and provide actionable insights for environmentally responsible decision-making. The platform integrates a modern web-based architecture consisting of React.js, Node.js, Express.js, MongoDB, and Ollama-based Large Language Models (LLMs) to deliver intelligent emission analysis and personalized sustainability recommendations. CarbonLens enables users to record daily activities related to transportation, energy consumption, dietary habits, and other carbon-generating behaviors. The system automatically estimates carbon emissions using AI-assisted activity analysis and categorizes them into meaningful sustainability metrics. Interactive dashboards provide real-time emission visualization, carbon score tracking, weekly trend analysis, category-wise breakdowns, and personalized recommendations aimed at reducing environmental impact. The platform also includes secure authentication, activity history management, report generation, and customizable themes to enhance usability and accessibility. Experimental evaluation demonstrates the effectiveness of AI-assisted emission estimation and the usefulness of interactive analytics in promoting sustainable behavioral changes. CarbonLens contributes toward environmental awareness by combining artificial intelligence, data analytics, and user-centric design to create an accessible and scalable sustainability monitoring solution.
Authors
- Sejal Jain
- Sanskar Rathore
- Pranav Singh
- Sachin kushwaha
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-06-17
- DOI
- https://doi.org/10.5281/zenodo.20742940
- Primary Topic
- Air Quality Monitoring and Forecasting
- Type
- article
- Field-Weighted Citation Impact
- 0.00