fairfolio
Saved Projects

AI powered Air Quality Prediction System

CSEF · 2026 Environmental Engineering (Senior Division)

Joowon Kang

Overview

Air quality impacts everyone, yet monitoring is often expensive. To solve this, we developed a computer vision system that estimates air quality directly from sky images. We hypothesized that visual cues contained relevant information regarding pollution. We trained a convolutional neural network to analyze images for air quality prediction. The model learned to extract features from the images, which were processed by a classification head to predict the air quality. The model was then optimized by minimizing the loss between predicted and actual labels. For data collection, we gathered over 7,000 images across two continents. Each image was then paired with local sensor readings, allowing us to create an organized dataset. Using this, we were able to train our model to achieve over 80% accuracy. This demonstrated that sky images provide meaningful data when predicting air quality, allowing us to establish a new foundation for monitoring systems.

Competition history

  • CSEF 2026 Environmental Engineering (Senior Division) · Entry S-11-16

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google