We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Hybrid Ensemble Machine Learning Models with SHAP Explainability for Robust Prediction of Suspended Particle Attachment Efficiency in Complex Environmental Systems
Summary
Scientists developed a new computer model that can better predict how tiny particles—including microplastics—clump together and move through the environment. The model found that salt levels in water are the main factor controlling how single particles stick together, while electrical charge differences matter most when different types of particles interact. This research could help us better understand how microplastics and other harmful particles spread through water systems and potentially affect human health.
The accurate prediction of aggregation attachment efficiency (α) is critical for suspended nanoparticle and microplastic fate in environmental systems, yet existing models struggle with nonlinear interactions and limited interpretability. This study evaluates two recently proposed hybrid ensemble machine learning frameworks, Improved Harris Hawks Optimized XGBoost (IHHO-XGBoost) and AdaBoost-ExtraTrees, for predicting α across mono- and binary-particle systems. Using a curated dataset spanning diverse particle types and environmental conditions, we demonstrate that IHHO-XGBoost outperforms six benchmark algorithms, achieving test R2 values of 0.865 (mono particle) and 0.797 (binary particle). SHAP analysis reveals distinct mechanistic drivers: salt concentration dominates mono particle aggregation, while zeta potential asymmetry controls binary systems. By adapting these advanced ensembles to colloidal stability prediction, this work provides a computational framework for improving the prediction of particle interactions in complex environmental matrices.
Sign in to start a discussion.
More Papers Like This
Predictive modeling of microplastic adsorption in aquatic environments using advanced machine learning models
Scientists used advanced machine learning models to predict how microplastics interact with and absorb organic pollutants in water. The results showed that microplastics with certain chemical properties attract more toxic compounds, which matters because contaminated microplastics in waterways can concentrate harmful chemicals that may eventually reach humans through drinking water and seafood.
Hybrid modeling of hetero-agglomeration processes: a framework for model selection and arrangement
Researchers developed a hybrid modeling framework for hetero-agglomeration processes — the clumping together of different particle types — to better predict how microplastics interact with natural particles in aquatic environments. The framework helps select appropriate models for different environmental conditions and particle combinations.
The suspension stability of nanoplastics in aquatic environments revealed using meta-analysis and machine learning
Researchers combined machine learning and meta-analysis to model nanoplastic aggregation behavior in water, finding that surface charge is the dominant factor, and predicting that nanoplastics will aggregate and settle in estuarine and low-flow conditions such as those found in China's Poyang Lake.
Rapidly Predicting Aqueous Adsorption Constants of Organic Pollutants onto Polyethylene Microplastics by Combining Molecular Dynamics Simulations and Machine Learning
Researchers developed a computational method combining molecular simulations with machine learning to rapidly predict how organic pollutants adsorb onto polyethylene microplastics in water. The approach accurately predicted adsorption behavior across different conditions including particle size, water salinity, and pH without requiring time-consuming laboratory experiments. The tool could help environmental scientists more quickly assess how microplastics interact with and transport chemical contaminants in aquatic environments.
Modified Stochastic Model for Settling and Rising Microplastic Transport in Open Channel Flows
Scientists created a new computer model to better predict how tiny plastic particles move through rivers and streams. Unlike previous models that assumed all particles sink like dirt and sand, this new model accounts for the fact that some microplastics float upward because they're lighter than water. This better understanding of where microplastics end up in waterways could help protect drinking water sources and reduce human exposure to plastic pollution.