A novel spectroscopy-deep learning approach for aqueous multi-heavy metal detection

Abstract

Addressing heavy metal contamination in water bodies is a critical concern for environmental scientists. Traditional detection methods are often complex and costly. Recent advancements in artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), have shown significant potential in analytical chemistry. However, these AI models require extensive spectral data, which traditional methods struggle to provide quickly. To overcome this challenge, we developed a new digital spectral imaging system and rapidly collected 3000 digital spectra from mixed heavy metal samples. We then created an end-to-end regression model for predicting heavy metal concentrations in mixed water samples using deep convolutional neural networks (ResNet-50, Inception V1, and SqueezeNet V1.1). The results indicated that the trained ResNet-50 model can effectively detect arsenic, chromium, and copper simultaneously, with a linear fitting coefficient exceeding 0.99 between true and predicted values. This study offers an efficient approach for rapid heavy metal detection in complex water environments and serves as a reference for developing intelligent analytical techniques.