Development of AI-Powered Technology for Automatic Identification of Contaminants

A research team at Kyung Hee University has developed a sensor technology that combines gold nanoparticles, which autonomously change their structure upon contact with water, with artificial intelligence (AI) to detect and identify micro- and nanoplastics in water with ultra-high sensitivity.

Professor Jungmok Yoo from the Department of Convergence Bio and New Materials Engineering at Kyung Hee University and Professor Daehyun Jeong from the Department of Smart Farm Science research team have developed a surface-enhanced Raman scattering (SERS) sensor that detects micro- and nanoplastics with high sensitivity. Research schematic. Kyung Hee University

Professor Jungmok Yoo from the Department of Convergence Bio and New Materials Engineering at Kyung Hee University and Professor Daehyun Jeong from the Department of Smart Farm Science research team have developed a surface-enhanced Raman scattering (SERS) sensor that detects micro- and nanoplastics with high sensitivity. Research schematic. Kyung Hee University

View original image

On August 26th, Kyung Hee University announced that the joint research team led by Professor Jungmok Yoo of the Department of Convergence Bio and New Materials Engineering and Professor Daehyun Jung of the Department of Smart Farm Science had developed a highly sensitive surface-enhanced Raman scattering (SERS) sensor that automatically analyzes various contaminants in complex samples.


Micro- and nanoplastics are extremely small and exist in trace amounts, making it difficult for conventional sensors to sufficiently amplify detection signals. To address this challenge, the research team focused on the properties of regenerated cellulose hydrogel, which expands in volume when in contact with water.


By arranging gold nanoparticles on the surface of the hydrogel, the team succeeded in inducing the particles to actively realign around the nanoplastics upon moisture absorption, forming high-density "hotspots" that strongly amplify the detection signal.


The research team demonstrated excellent detection performance not only for polystyrene nanoplastics ranging from 80 to 850 nanometers in size, but also in various environmental samples such as reservoir water, tap water, milk, and simulated seawater.


Additionally, the researchers integrated a multilabel AI model trained on composite spectra to enable automatic and precise identification of each component in complex contaminated samples, including nanoplastics, organic dyes, and residual pesticides mixed together.


Professors Jungmok Yoo and Daehyun Jung stated, "The key was utilizing the hydrogel not merely as a support, but as a functional material that actively changes the structure of nanoparticles," adding, "We aim to further expand this technology into portable sensors capable of rapidly and accurately analyzing various complex environmental pollutants in the field."



This research achievement was published in the latest issue of 'Advanced Functional Materials' (Impact Factor = 19.9), a globally renowned journal in the field of materials science.


This content was produced with the assistance of AI translation services.

© The Asia Business Daily. All rights reserved. Unauthorized AI training and use prohibited.

Today’s Briefing