EnviroCast Risk AI

Inspiration

What it does

• Predicts future temperature trends
• Assigns environmental risk levels
• Visualizes projections using charts
• Provides an easy-to-use web interface

How we built it

The project was built using Python and Flask for the backend, with a machine learning model trained on historical climate data.

The frontend was developed using HTML, JavaScript, and Chart.js for data visualization. The system communicates via a REST API and runs entirely locally.

Challenges we ran into

• Finding and preparing climate data
• Designing a simple but meaningful prediction model
• Connecting frontend and backend securely

Accomplishments that we're proud of

• Built a working AI-based prediction system
• Successfully integrated real climate data
• Created a clean and functional demo interface

What we learned

• How to apply machine learning to real-world environmental problems
• How to build a full-stack AI project
• How to present technical ideas clearly

What's next for EnviroCast Risk AI

• Add additional environmental risk factors such as air pollution (PM2.5)
• Improve prediction accuracy with more datasets
• Deploy the application online for public use

Built With

• a
• climate
• historical
• learning
• machine
• model
• on
• the-project-was-built-using-python-and-flask-for-the-backend
• trained
• with