Machine learning-assisted fluorescence visualization for sequential quantitative detection of aluminum and fluoride...

Area of Science:

• Environmental Science
• Analytical Chemistry
• Materials Science

Background:

• Aluminum (Al³⁺) and fluoride (F⁻) ions pose environmental and health risks.
• Accurate and efficient monitoring of these ions is crucial.
• Existing detection methods may lack sensitivity or efficiency.

Purpose of the Study:

• To develop a novel, accurate, and efficient fluorescence-based method for sequential quantitative analysis of Al³⁺ and F⁻ ions.
• To leverage machine learning for enhanced detection accuracy.
• To provide a valuable tool for environmental monitoring and risk assessment.

Main Methods:

• Synthesis of sulfur-functionalized carbon dots (C-dots) as fluorescence probes.
• Sequential detection utilizing fluorescence enhancement by Al³⁺ and quenching by F⁻.
• Image feature extraction using Python computer vision, followed by K-means clustering and principal component analysis (PCA) regression.

Main Results:

• Achieved a detection limit of 4.2 nmol/L for Al³⁺ and 47.6 nmol/L for F⁻.
• K-means clustering showed excellent performance, indicated by the average Silhouette Coefficient.
• PCA-based regression analysis provided precise quantitative results for both ions.

Conclusions:

• The developed machine learning model demonstrates high accuracy and sensitivity for Al³⁺ and F⁻ detection.
• This approach offers a significant advancement in environmental monitoring techniques.
• The method is valuable for safeguarding ecosystems and public health through effective risk assessment.