Leveraging machine learning for microplastic detection, global distribution analysis, and management.

Area of Science:

• Environmental Science
• Analytical Chemistry
• Data Science

Background:

• Microplastic (MP) pollution is a global environmental challenge requiring advanced detection and management strategies.
• Significant MP pollution hotspots identified in India (Netravathi River), China (Wuhan lakes), and the USA (San Francisco Bay).

Purpose of the Study:

• To review and emphasize the integration of Artificial Intelligence (AI) and Machine Learning (ML) with analytical techniques for microplastic research.
• To explore foundational concepts, data resources, preprocessing methods, and limitations of ML algorithms in MP identification, detection, distribution, and management.

Main Methods:

• Combining AI with analytical techniques such as Raman spectroscopy (RS), Fourier transform infrared spectroscopy (FTIR), image processing (IP), and hyperspectral imaging (HSI).
• Application of Machine Learning (ML) algorithms with FTIR, Raman, and HSI for enhanced MP detection and characterization.

Main Results:

• AI-driven analytical techniques significantly improve the efficiency, accuracy, and scalability of microplastic detection.
• ML algorithms integrated with FTIR, Raman, and HSI achieved high detection efficacy (99%, 99.1%, and 97% respectively).

Conclusions:

• AI and environmental science offer revolutionary tools for real-time monitoring and mitigation of microplastic pollution.
• Further research into combining ML technologies is crucial for advancing microplastic research and preserving ecosystem health.