MICRO PLASTIC DETECTION

Abstract

Microplastics are tiny plastic particles less than 5 mm in size that have emerged as a serious environmental concern due to their persistence, widespread distribution, and potential impact on ecosystems and human health. These particles originate from the degradation of larger plastic waste or from primary sources such as cosmetics, synthetic fibers, and industrial processes. Microplastics are commonly found in oceans, rivers, soil, drinking water, and even in the food chain. Detecting microplastics accurately is essential for monitoring pollution levels and developing effective mitigation strategies.This study focuses on the detection and analysis of microplastics using advanced analytical techniques such as spectroscopy, microscopy, and Deep Learning methods. Techniques like VGG16 and EfficientNet-B0are widely used for identifying polymer types and particle morphology. Recently, Deep Learning Algorithms have been integrated to automate classification and improve detection accuracy.The proposed microplastic detection system aims to provide a reliable, costeffective, and efficient method for identifying microplastic particles in water samples. The system includes sample collection, filtration, image processing, and material characterization. By combining traditional laboratory techniques with modern Deep Learning approaches, the detection process becomes faster and more precise.Effective microplastic detection not only supports environmental monitoring but also contributes to policymaking, waste management strategies, and sustainable development goals. Continuous research in this area will help reduce plastic pollution and protect marine life and human health from long-term ecological damage