CNN for scalar-source distance estimation in grid-generated turbulence

Countermeasures against material leakage in industrial plants call for rapid leak source estimation techniques based on limited downstream information. Assuming that such scalar diffusion occurs in a turbulent environment, it is necessary to extract features from its instantaneous local concentration distribution and estimate the distance from the observation point to the source. To this end, we proposed an estimation method using a supervised deep learning of a convolutional neural network (CNN) and investigated its estimation performance in grid-generated turbulence fields. The grid turbulence fields were reproduced by direct numerical simulations at three Reynolds numbers ( R e ), and the CNN was trained using two-dimensional distribution images of passive scalars downstream. We confirmed that the images large enough to cover the spatial integral length scales of the scalar resulted in high estimation accuracy. For images with a coarsened brightness gradation, the small-scale feature of scalar fluctuations was lost, and the CNN attained a low estimation accuracy. By training the CNN with high- R e images, a high estimation accuracy was obtained, even for low- R e images. The opposite case (low- R e training and high- R e estimation) yielded low accuracy, where the CNN significantly underestimated the distance against the source. Based on these results, we discussed the generalizability and essential features to be learned by the CNN. • Supervised deep learning to estimate the distance from an upstream scalar source. • Instantaneous scalar fluctuations in a finite 2D observation window as input data. • DNS-provided data for grid-generated turbulence with passive scalar transport. • Dependence of the estimation performance on the observation window size and shape, brightness gradation, and Reynolds number during training/testing. • High generalization performance achieved by training with a high Reynolds number.