Machine Learning Prediction of Adsorption Behavior of Xenobiotics on Microplastics under Different Environmental Conditions

Machine learning models successfullypredicted the adsorptionbehavior of xenobiotics on microplastics and revealed the impact ofxenobiotic properties, microplastic types, and environmental factorson the interactions of xenobiotics and microplastics. Therehave been mounting concerns over microplastics as a vectorof environmental xenobiotics recently. Adsorption plays a pivotalrole in this process, which varies with the properties of xenobiotics,the characteristics of microplastics, and environmental conditions.The vast number of xenobiotics and the diversity of microplastics,as well as the continuous weathering of microplastics in the environment,make it unrealistic to measure the adsorption capacity and affinityof each combination of xenobiotics, microplastics, and environmentalconditions in laboratory studies. Random Forest (RF) and ArtificialNeural Network (ANN) algorithms were used to predict the adsorptionaffinity of xenobiotics on microplastics and elucidate the impactof environmental parameters. pH is responsible for a large variationin the results through its effect on the dissociation of ionizablexenobiotics and the surface charge of microplastics. The aging statusof microplastics had a smaller but still significant impact on adsorptionaffinity, with pristine particles generally having a higher affinity.The results shed light on the potential alteration of the fate andimpact of xenobiotics by microplastics. As more data become availablein the future, the precision of machine learning (ML) models can befurther improved. Overall, our study demonstrated the potential ofML in predicting the adsorption of a wide range of xenobiotics onmicroplastics.