Magnetic‐optical dual functional Janus particles for the detection of metal ions assisted by machine learning

Abstract

Functional polymer microspheres have broad application prospects in various fields, such as metal ion detection, adsorption, separation, and controlled drug release. However, integrating different functions in a single microsphere system is a significant challenge in this field. In this work, we prepared multicompartmental emulsion droplets utilizing microfluidic technology. Fe3O4 magnetic nanoparticles were added to one of the compartments of the emulsion droplets as functional particles, and Janus microspheres were obtained after curing. Fluorescent probes enter the two compartments of the Janus microspheres by diffusion. The fluorescence changes of the microspheres were observed in situ and captured through a fluorescence microscope. The images are processed by image recognition software and a Python program. The “fingerprint” of the detected metal ions is obtained by dimensionality reduction of the data through Principal Component Analysis. We employ different algorithms to build Machine Learning models for predicting the metal ion species and concentration. The variation of fluorescence intensity of the three fluorescent probes and the corresponding R, G, and B channel values and time are used as descriptors. The results show that the Random Forest, K‐neighborhood (KNN), and Neural Network models demonstrated a better predicted effect with a variance (R2) greater than 0.9 and a smaller root mean square error; among them, the KNN model predicted the most accurate results.

Prediction and Interpretability Study of the Glass Transition Temperature of Polyimide Based on Machine Learning with Quantitative Structure–Property Relationship (Tg-QSPR)

“…Emerging polymer informatics − provides a novel approach that leverages the development of advanced machine learning algorithms to establish quantitative structure–property relationship (QSPR). This enables discovery of new PI materials before laboratory synthesis and testing, thereby shortening the development cycle and transforming traditional trial-and-error experimental methods into theoretical prediction-guided experiments. − For example, Liu collected 54 types of aromatic heterocyclic PI materials and developed a QSPR model using the artificial neural network backpropagation algorithm to predict T g . The model achieved a root mean squared error (RMSE) of 16.4 °C and a correlation coefficient ( R ) of 0.937 on the testing set (18 samples).…”