fairfolio
Saved Projects

FreshAlert: A Novel AI-Driven Approach to Food Spoilage Detection for Reducing Household Food Waste

CSEF · 2026 Environmental Engineering (Track 2) (Senior Division)

Arshia Sankar, Laya Sunkara

Overview

Approximately 931 million tons of food were wasted globally in 2019, with spoilage as a major contributor. Most homes rely on visual and smell-based spoilage checks, missing unsafe microbial progressions. This project developed and validated a reusable smart food-storage box that continuously collects sensor data and monitors food to predict spoilage over time. We engineered a food-safe container equipped with an Arduino Nicla Vision platform and gas and environmental sensors (VOC/eCO2, CO2, temperature, humidity, and ammonia-related sensing). Data was collected every 30 seconds and analyzed in 6-minute buckets. We used a gradient boosting regression (GBR) classification algorithm to model spoilage on a 5-stage scale (Fresh to Spoiled) and a GBR quantile algorithm to predict a time-to-spoilage range. Test 1 ran until bacterial and visual testing confirmed spoilage; this dataset was used to calibrate and lock the model. Test 2 was an in-progress validation run to evaluate projection performance on new data. On Test 1, the model achieved 99.67% stage classification accuracy and 99.51% recall. Transition timing error averaged 2.06 hours overall, with Stage 2-4 transitions within ≤7 minutes, while Stage 5 showed the largest error and remains the main area for further trials. On Test 2, the locked model projected progression correctly for the ongoing run. We designed a dashboard to display spoilage status (stage and time-to-spoilage) in a user-friendly manner. Results indicate that continuous sensing provides practical early warnings of spoilage and helps reduce food waste in households and industrial settings through earlier, data-driven decisions.

Competition history

  • CSEF 2026 Environmental Engineering (Track 2) (Senior Division) · Entry S-12-08

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