Predicting adsorption capacity of pharmaceuticals and personal care products on long-term aged microplastics using machine learning

We investigated the adsorption mechanism of 66 coexisting pharmaceuticals and personal care products (PPCPs) on microplastics treated with potassium persulfate, potassium hydroxide, and Fenton reagent for 54, 110, and 500 days. The total adsorption capacity (qe) of 66 PPCPs on 15 original microplastics was 171.8 – 1043.7 μg/g, far below that of 177 long-term aged microplastics (7114.0 – 13114.4 μg/g). Around 69.8% of qe was primarily influenced by the total energy, energy of the highest occupied molecular orbital, and energy gap of PPCPs, calculated using the B3LYP/6-31 G* level. Furthermore, 111 aged microplastics exhibited similar total qe values. Additionally, we developed predictive models based on attenuated total reflectance Fourier transform infrared spectroscopy to predict the individual and total qe on 192 microplastics. These models, including the maximal information coefficient and gradient boosting decision tree regression, exhibited high accuracy with Rtraining2 values of 0.9772 and 0.9661, respectively, and p-values below 0.001. Spectroscopic analysis and machine learning models highlighted surface functional group alterations and the importance of the 1528 - 1700 cm-1 spectral region and carbon skeleton in the adsorption process. In summary, our findings contribute to understanding the adsorption of PPCPs on microplastics, particularly in the context of long-term aging effects.