Related Experiment Video
Updated: Sep 8, 2025
07:58
A Polyaniline-based Sensor of Nucleic Acids
Published on: November 1, 2016
8.1K
Quantitative Colorimetric Detection of Dissolved Ammonia Using Polydiacetylene Sensors Enabled by Machine Learning
Papaorn Siribunbandal1,2, Yong-Hoon Kim3, Tanakorn Osotchan4
1Department of Physics, Faculty of Science and Technology, Thammasat University, Pathumthani 12121, Thailand.
ACS Omega
|June 13, 2022
Summary
This study presents a novel polydiacetylene (PDA) sensor for easy, on-site detection of dissolved ammonia. Machine learning enhances naked-eye colorimetric detection for accurate aquatic ecosystem monitoring.
Area of Science:
- Environmental Science
- Materials Science
- Analytical Chemistry
Background:
- Dissolved ammonia poses significant risks to aquatic ecosystems and aquaculture.
- Accurate and accessible detection methods are crucial for environmental management.
- Current methods may lack on-site capabilities or ease of use.
Purpose of the Study:
- To develop a simple, naked-eye detectable sensor for quantitative dissolved ammonia monitoring.
- To integrate polydiacetylene (PDA) sensors with machine learning for enhanced accuracy.
- To enable on-site, real-time ammonia detection in aquatic environments.
Main Methods:
- Fabrication of polydiacetylene (PDA) vesicles via green chemical synthesis.
- Utilizing the blue-to-red color transition of PDA upon ammonia exposure for detection.
- Quantitative analysis using UV-vis spectroscopy and image-based machine learning (support vector machine).
Main Results:
- The PDA sensor showed a clear color transition detectable by the naked eye.
- Achieved a detection limit below 10 ppm ammonia with a 20-minute response time.
- High classification accuracy (100% with scanner, 95.1% with smartphone) using machine learning on colorimetric images.
Conclusions:
- Developed PDA sensors offer a simple, accurate, and stable method for dissolved ammonia detection.
- Integration with machine learning and smartphone imaging enables effective on-site monitoring.
- This technology holds promise for improved management of aquatic ecosystems and aquaculture.
