AUTHOR=Murillo Michael S. TITLE=Data-driven electrical conductivities of dense plasmas JOURNAL=Frontiers in Physics VOLUME=Volume 10 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/physics/articles/10.3389/fphy.2022.867990 DOI=10.3389/fphy.2022.867990 ISSN=2296-424X ABSTRACT=A wide range of theoretical and computational models have been developed to predict the electrical transport properties of dense plasmas. These developments have been driven in part because dense plasma experiments explore order-of-magnitude excursions in temperature and density; in experiments with mixing, there may also be excursions in stoichiometry. In contrast, as high pressures create transient and heterogeneous plasmas, data from experiments that isolate transport is relatively sparse. However, the aggregate of our datasets continues to increase in size, playing a key role in the validation of transport models. This trend suggests the possibility of using the data directly to make predictions, either alone or in combination with models, thereby creating a predictive capability with a controllable level of agreement with the data. Here, such a data-driven model is constructed by combining a theoretical model with extant data, using electrical conductivity as an example. The data are first detrended using a theoretical model appropriate for dense plasmas over wide ranges of conditions. That discrepancy is learned via a modified radial basis function neural network. Regularization of the network is included through careful choice of centers using silhouette scores from k-means clustering. The covariance properties of each cluster are used in a scaled Mahalanobis distance metric to construct anisotropic basis functions for the network.