Aqueous adsorption, a long-standing separation/purification process, has been continuously investigated for decades. Studying the sorption of contaminants in soils is important for understanding the fate of the contaminants and properly assessing the related environmental risks. However, existing experimental methods and traditional models for quantifying sorption, such as adsorption isotherm, multilinear regression, and surface complexation models, are time-consuming to obtain and are ineffective. In this research, we first built a machine learning modeling process based on neural networks, a group-selection data-splitting strategy for grouped adsorption data for adsorbent-adsorbate pairs under different equilibrium concentrations, and poly-parameter linear free energy relationships for aqueous adsorption of 165 organic compounds onto 50 biochars, 34 carbon nanotubes, 35 GACs, and 30 polymeric resins. Because there are almost always multiple contaminants coexisting in the natural environment or water treatment processes, we further combined the adsorbed solution theory and a neural network to develop models for the prediction of bi-solute adsorption. We then developed machine learning models for the soil sorption of 6 heavy metals (Cd(II), Cr(VI), Cu(II), Pb(II), Ni(II), and Zn(II)) using 4420 data points (1105 soils). The global distribution of heavy metal sorption capacities on soils was then predicted with known soil properties. Our ongoing work focuses on developing predictive models for the sorption of many organic compounds toward a diverse range of soils and sediments. Overall, these models will greatly help mitigate and assess the risks associated with thousands of organic contaminants and heavy metals in engineered and natural environments.
About the Speaker:
Dr. Huichun (Judy) Zhang is the Frank H. Neff professor in the Department of Civil and Environmental Engineering at Case Western Reserve University. She earned her Ph.D. from the Georgia Institute of Technology (US) and her B.S. and M.S. from Nanjing University (China). Her research focuses on the fate and transformation of environmental contaminants in natural and engineered aquatic environments and the removal of organic contaminants from contaminated water. Her recent research also includes predictive modeling for contaminant reactivity and sorption using classical models and machine learning tools. Dr. Zhang has published in numerous journals, such as Chemical Reviews, Environmental Science and Technology, and Water Research. She has received six competitive research grants from the U.S. National Science Foundation as the single/lead PI. In addition, Dr. Zhang directed research projects for many other federal, state, and private funding agencies. She is a Topic Editor for ACS ES&T Water and an Associate Editor for Frontiers of Environmental Science and Engineering (FESE). She is a past recipient of the Nanova/CAPEES Frontier Research Award.