Toxic gas release modeling for real-time analysis using variational autoencoder with convolutional neural networks

High-accuracy gas dispersion models are necessary for predicting toxic gas movement, and for reducing the damage caused by toxic gas release accidents in chemical processes. In urban areas, where obstacles are large and abundant, computational fluid dynamics (CFD) would be the best choice for simulating and analyzing scenarios of accidental release of toxic chemicals. However, owing to the large computation time required for CFD simulation, it is inappropriate in emergency situations and in real-time alarm systems. In this study, a non-linear surrogate model based on deep learning is proposed using a variational autoencoder with deep convolutional layers and a deep neural network with batch normalization (VAEDC-DNN) for real-time analysis of the probability of death (P_death). VAEDC can extract representation features of the P_death contour with complicated urban geometry in the latent space, and DNN maps the variable space into the latent space for the Pdeath image data. The chlorine gas leak accident in the Mipo complex (city of Ulsan, Republic of Korea) is used for verification of the model. The proposed model predicts the P_death image within a mean squared error of 0.00246, and compared with other models, it exhibits superior performance. Furthermore, through the smoothness of image transition in the variable space, it is confirmed that image generation is not overfitting by data memorization.