We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Microplastic Pollution Prediction
Summary
This machine learning project used XGBoost and environmental variables (ocean currents, sea surface temperature, proximity to cities) to predict microplastic hotspots in marine environments. The model achieved high accuracy and could help environmental agencies prioritize cleanup efforts without expensive field sampling.
Microplastic contamination poses serious risks to marine life, ecosystems, and human health. Identifying high-risk areas is challenging due to complex environmental factors. This project proposes a machine learning-based model—using data like ocean currents, sea surface temperature, and proximity to cities—to predict microplastic hotspots. By applying techniques like XGBoost, the model achieves high accuracy and helps environmental agencies target cleanup efforts efficiently. It reduces the need for costly field sampling and showcases how AI can enhance sustainability and environmental monitoring. INDEX TERMS: :Microplastic Pollution, Environmental Monitoring, Machine Learning, XGBoost, Ocean Current Dynamics, Sea Surface Temperature, Predictive Modeling, Aquatic Ecosystems, Supervised Learning, Data Preprocessing, Feature Engineering, Artificial Intelligence (AI), Sustainability, Pollution Hotspots, Geographic Information System (GIS).