Fig. 17From: Reduced-order modeling for stochastic large-scale and time-dependent flow problems using deep spatial and temporal convolutional autoencodersComparison of the relative \(L^{2}\)-error of the mean and standard deviation of the water level as a function of time based on the POD-ANN technique and the proposed NIROM-CAEs approach. Errors are computed with respect to the reference LHS solution (with \(N_{s}=2000\) realizations)Back to article page