No Nurdles: Novel Model for Predicting and Preventing Plastic Pellet/Nurdle Spills

Overview

Plastic nurdles—small industrial plastic pellets used in manufacturing—are a major yet under-monitored source of global microplastic pollution. An estimated 445,970 metric tons of nurdles enter the environment annually, impacting over 220 aquatic species and contributing significantly to long-term ecosystem degradation. Despite their prevalence, real-time detection, prediction, and documentation of nurdle spills remain limited. No Nurdles is a web-based application developed to address this gap by integrating citizen science, environmental datasets, and artificial intelligence into a unified monitoring and prediction system. The application includes five core components: an Interactive Map, Confidence Scoring system, Nurdle Identifier, Nurdle Predictor, and Advocacy interface. The Interactive Map visualizes historical nurdle sightings, model-generated spill predictions, and confidence scores, allowing users to analyze spatial and temporal distribution patterns. Confidence scores are generated through an algorithm that evaluates historical spill data alongside environmental variables to estimate spill likelihood. The Nurdle Identifier uses a custom-trained image classification model built with TensorFlow.js and Teachable Machine to classify uploaded images as “Nurdle” or “No Nurdle,” enabling accurate field identification without specialized equipment. The Nurdle Predictor applies machine learning techniques to environmental datasets, including wind patterns, ocean currents, and past spill records, to predict the probability, timing, and location of future spills. Initial model testing achieved prediction confidence levels up to 95% for historical spill events. Utilizing public observations and environmental data, No Nurdles enhances accessibility, supports proactive mitigation, and provides a scalable framework for addressing microplastic pollution before spills escalate.

Competition history

• CSEF 2026 Earth & Environmental Sciences(Senior Division) · Entry S-08-20

Related projects

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

Browse more like this

• All Earth and Environmental Sciences projects
• CSEF Earth and Environmental Sciences projects
• Every CSEF 2026 project