A novel method for micropollutant quantification using deep learning and multi-objective optimization. (1st April 2022)

• Record Type: Journal Article
• Authors: Yun, Daeun; Kang, Daeho; Jang, Jiyi; Angeles, Anne Therese; Pyo, JongCheol; Jeon, Junho; Baek, Sang-Soo; Cho, Kyung Hwa
• Is Part Of: Water research. Volume 212(2022)
• Publication Date: 2022-04-01
• Subjects: Micropollutant -- Surrogate method -- High resolution mass spectrometry -- Deep learning -- Convolutional neural network; Water -- Pollution -- Research -- Periodicals; 363.7394
• DOI: 10.1016/j.watres.2022.118080
• Languages: English
• ISSNs: 0043-1354

Abstract

Highlights: Eighteen substances were quantified using deep learning and optimization process. Multi-objective optimization identified the optimal model and type of standards. DarkNet-53 model using nine standards yielded the highest model performance. Abstract: Micropollutants (MPs) released into aquatic ecosystems have adverse effects on public health. Hence, monitoring and managing MPs in aquatic systems are imperative. MPs can be quantified by high-resolution mass spectrometry (HRMS) with stable isotope-labeled (SIL) standards. However, high cost of SIL solutions is a significant issue. This study aims to develop a rapid and cost-effective analytical approach to estimate MP concentrations in aquatic systems based on deep learning (DL) and multi-objective optimization. We hypothesized that internal standards could quantify the MP concentrations other than the target substance. Our approach considered the precision of intra-/inter-day repeatability and natural organic matter information to reduce instrumental error and matrix effect. We selected standard solutions to estimate the concentrations of 18 MPs. Among the optimal DL models, DarkNet-53 using nine standard solutions yielded the highest performance, while ResNet-50 yielded the lowest. Overall, this study demonstrated the capability of DL models for estimating MP concentrations.