Enhancing Environmental Sustainability: AI-Enabled Plastic Waste Classifications

Plastic waste has reached critical thresholds over the recent years, requiring innovative solutions to preserve the environment’s health. Plastics, extensively used in households, pose a grave threat to the environment. The United Nations aims to reduce plastic pollution by 80% by 2040, highlighting the urgency of the issue. Conventional waste-sorting techniques, often manual, are prone to errors and prove to be inefficient, hinder the process of recycling. Presenting a promising solution, this research focuses on the accurate classification of plastic waste, encompassing Polyethylene Terephthalate (PET), High-Density Polyethylene (HDPE), Polypropylene (PP), and Polystyrene (PS). The methodology employs artificial intelligence (AI) and deep learning, specifically leveraging Convolutional Neural Networks (CNNs). Using the WaDaBa Dataset, containing 4000 images of municipal plastic waste, the study utilizes the MobileNetV2 model for its efficiency and resource-conscious design. By using Artificial Intelligence driving systems, plastic waste can be effectively recycled to significantly improve recycling and sustainability.