“…As machine learning techniques become increasingly more ubiquitous for scientific visualization and analysis, latent representations generated by autoencoders have attracted great attentions of researchers in recent years. Latent representations have been successfully demonstrated to retain essential information in the original data, and can be used for similarity analysis [11,12,18,25,28], generation of visualizations [6], synthesis of simulations [22,42,43], data reductions [26,44], and have been applied to multivariate volumetric data [28], streamlines and stream surfaces [18], isosurfaces [12], and particles [25].…”