The paper “Ensemble-based method for the inverse Frobenius–Perron operator problem: Data-driven global analysis from spatiotemporal “Movie” data“, co-authored by Naratip Santitissadeekorn and Erik Bollt (Clarkson University), has been published in Physica D (link here). It appears in a special issue on “Machine Learning and Dynamical Systems”. The paper’s ensemble-based approach improves the parameter inferences from density evolution. The theory is applied to the assessment of uncertainty of coherent structure identification. The graphic below is Figure 9 from the paper showing application of the theory.