We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
AI-driven portable smartphone-based sensor for microplastic detection: a comprehensive review
Summary
Researchers reviewed AI-integrated smartphone sensors for microplastic detection and found that systems combining convolutional neural networks with optical sensing achieve 96–99% accuracy, offering a portable and affordable alternative to laboratory methods that could enable large-scale distributed environmental monitoring.
Microplastic pollution is a major environmental concern, with millions of metric tons entering the oceans yearly, threatening marine ecosystems and human health. This underscores the urgency for accessible, real-time microplastic detection technologies. This review examines the fusion of artificial intelligence (AI) with smartphone-based sensors, aiming to develop portable, cost-efficient microplastic detection systems, and ushering a transition from laboratory-centered to distributed environmental monitoring. The review covers traditional microplastic detection methods such as FTIR and Raman spectroscopy and introduces emerging AI-driven techniques. It discusses advances in optical sensing (plasmonic nanowhiskers, fluorescence staining, colorimetric assays) and AI models, such as CNNs, YOLOv8, and U-Net. Smartphone hardware and computational advancements are also evaluated. AI-enhanced smartphone sensors show detection accuracies between 96% and 99.3%, outperforming conventional microscopy and approaching laboratory-level precision. These systems detect sub-micron microplastics efficiently, supported by economic analyses favoring wide deployment. AI-integrated smartphone sensors are transformative tools for environmental monitoring, offering portability, accuracy, and affordability. Continued innovation and regulatory support are essential for global adoption and effective microplastic pollution management.