Eli Goldberg's repositories
rfecvNano
The development of advection–dispersion particle transport models (PTM) for transport of nanoparticles in porous media has focused on improving model fit by inclusion of empirical parameters. However, this has done little to disentangle the complex behavior of nanoparticles in porous media and to provide mechanistic insights into nanoparticle transport. The most prominent limitation of current PTMs is that they do not consider the influence of physicochemical conditions of the experiments on the transport of nanomaterials. Here, we overcome this limitation by bypassing traditional advection–dispersion PTMs and relating the physicochemical conditions of the experiments to the experimental outcome using ensemble machine-learning methods. We identify a small set of factors that seem to determine the transport of nanoparticles in column experiments by recursive feature elimination with cross validation. .