10.6084/m9.figshare.8218421.v1 Jesper Soeren Dramsch Jesper Soeren Dramsch Gustavo Corte Gustavo Corte Hamed Amini Hamed Amini Colin MacBeth Colin MacBeth Mikael Lüthje Mikael Lüthje Including Physics in Deep Learning - An example from 4D seismic pressure saturation inversion figshare 2019 deep learning neural network residual physics 4D seismic seismic inversion inversion variational autoencoder Geophysics 2019-06-03 13:31:33 Presentation https://figshare.com/articles/presentation/Including_Physics_in_Deep_Learning_-_An_example_from_4D_seismic_pressure_saturation_inversion/8218421 Geoscience data often have to rely on strong priors in the face of uncertainty. Additionally, we often try to detect or model anomalous sparse data that can appear as an outlier in machine learning models. These are classic examples of imbalanced learning. Approaching these problems can benefit from including prior information from physics models or transforming data to a beneficial domain. We show an example of including physical information in the architecture of a neural network as prior information. We go on to present noise injection at training time to successfully transfer the network from synthetic data to field data.