Artificial intelligence assisted surface enhanced Raman scattering sensing achieves effective on-site analysis

Area of Science:

• Analytical Chemistry
• Spectroscopy
• Materials Science

Background:

• Surface-enhanced Raman scattering (SERS) provides sensitive, selective, and portable on-site detection without complex sample preparation.
• Challenges in SERS include matrix interference and large data volumes, limiting broader applications.
• Artificial intelligence (AI) offers solutions for SERS substrate design and spectral analysis accuracy.

Purpose of the Study:

• To review the latest developments in on-site detection and analysis using SERS integrated with AI (SERS-AI).
• To discuss optimizing signal acquisition, SERS substrate design, and AI-driven spectral analysis for field applications.
• To highlight SERS-AI applications in environmental monitoring, food safety, and medical diagnostics.

Main Methods:

• Optimizing target signal acquisition through rapid pretreatment and enhanced substrate-target affinity.
• Improving SERS substrate materials, focusing on hotspot quality and portability for on-site use.
• Integrating AI into SERS substrate synthesis and optimizing preparation with machine learning algorithms.

Main Results:

• AI integration enhances SERS substrate design and spectral analysis accuracy for on-site detection.
• Optimized pretreatment and substrate affinity improve signal acquisition under complex matrix interference.
• SERS-AI systems combined with portable spectrometers enable efficient data preprocessing and analysis.

Conclusions:

• SERS-AI technology effectively addresses challenges in on-site detection, improving sensitivity and accuracy.
• The integration of AI with SERS shows significant potential for diverse field analysis applications.
• This review provides theoretical and technical references for advancing SERS-AI in practical settings.