As the effects of the climate crisis become more visible every day, it has become critical to emphasize the importance of individual contribution. However, many people do not know the impact of their daily habits on the environment or do not know how to make changes.
At this point, we thought: Can artificial intelligence guide individuals' sustainable living decisions?
GreenMind was born with a vision that answered "yes" to this question. Our goal was to create a personal carbon footprint coach that everyone can easily understand and implement.
What it does GreenMind analyzes the user's lifestyle data to estimate their carbon footprint and offers personalized suggestions to reduce it. Features:
AI-Powered Carbon Estimation: Calculates carbon emissions by processing user data such as nutrition, transportation, and energy consumption.
Personal Action Plans: Generates suggestions such as "Ride your bike 2 days a week, save 4 kg of CO₂".
Traceability and Visualization: User can track their progress with graphs and be motivated with point systems.
Demo Mode: Interface that works with a sample user flow, providing quick demonstrations for the judges.
How we built it We trained a carbon estimation model with Python and scikit-learn.
We created a simple and effective user interface using Streamlit.
We sourced our data from publicly available carbon emission sources and user surveys.
We provided natural language, motivational recommendations with the OpenAI API.
Challenges we ran into Building a scalable data structure that accurately represents user habits was challenging.
We developed flexible algorithms to balance regional differences in carbon emission calculation metrics.
We had to fine-tune the “AI” recommendations to make them realistic and applicable.
Accomplishments that we're proud of We developed a simple AI model that works with minimal data but can provide meaningful suggestions.
We made our project understandable to everyone with an effective 5-minute demo flow.
As a team, we brought together technical competence, design and environmental awareness.
What we learned We realized how important it is to have clear suggestions for individuals to contribute to sustainability.
AI models require not only technical success but also ethical and user-friendly design.
“Artificial intelligence for social benefit” is possible with realistic solutions, not just conceptual ones.
What's next for GreenMind Reaching more users by developing a mobile application.
Adding API integrations that directly pull carbon emission data.
Increasing social impact by collaborating with local governments or environmental NGOs.
Establishing a more dynamic coaching system with real-time notifications based on user habits.
Log in or sign up for Devpost to join the conversation.