We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Recent Trends in Microplastic Detection based on Machine Learning and Artificial Intelligence
Summary
This chapter reviews recent trends in using machine learning and artificial intelligence for microplastic detection, addressing limitations of traditional microscopic and spectroscopic methods. The authors highlight how hyperspectral imaging combined with ML algorithms can classify and quantify microplastic samples more effectively, with improved recognition speed and cost-efficiency. The study suggests that AI-based approaches have significant potential for advancing large-scale microplastic monitoring.
Microplastics (MPs) have been regarded as a major global environmental issue in recent decades due to their toxic effects on fish and humans. Microscopic methods, Spectroscopic methods, and thermal analysis methods are traditionally used for the identification of MPs in environmental and experimental samples. However, these methods have several limitations such as limited particle size analysis, low resolution, low specificity, and expansiveness. With the advancement of technology, new methods using machine learning (ML) and computer vision for MP identification have been highlighted. The hyperspectral imaging with ML algorithms classifies and quantifies the samples effectively. This chapter mainly discusses different ML algorithm methods and deep learning models used to improve recognition, shorter detection, and cost-effectiveness. Moreover, Artificial Intelligence involves making automation systems to predict the severity with higher accuracy while maintaining a large database. These advancements have the potential to aid in the development of effective solutions for mitigating microplastic pollution.