Join us online: https://www.youtube.com/watch?v=5F9b0zwRqeg

Dr. Arthur Cheng, Professor at the National University of Singapore and ERL Fellow at MIT, presents "Shale anisotropy model building based on deep neural networks" at the MIT Earth Resources Laboratory.

"Seismic anisotropy parameters are essential in the processing and interpretation of modern array data with multi-component, long offsets, and wide azimuth acquisitions. Traditional well logs do not measure anisotropy in a vertical well and thus cannot provide the needed information. Conventional calibration-based as well as recent inversion-based rock physics modeling methods involve tuning parameters and subjective choices that are largely empirical and difficult to generalize. Here we present a machine learning (ML) approach to alleviate these problems. Since it is impossible to collect massive labelled field well log data, we generate paired synthetic data of features (porosity, density, vertical P- and S-wave velocities, P-wave and shear moduli) and labels (bulk and shear moduli of rock matrices, aspect ratio of ellipsoidal cracks). By tuning hyperparameters we obtain an optimal fully connected neural network with 4 hidden layers that fits well with the synthetic data. The neural network is applied to published laboratory measurements and field well log data from a Chinese well and a US well without any modification. We show that anisotropy models estimated by the deep neural network agree well with the inversion results and with the laboratory measurements. The neural network optimized by extensive training based on massive synthetic data removes the subjectivity in parameter selection, generalizes to different geological environments, and has the potential to provide real-time anisotropy estimation while logging." 

Arthur Cheng ScD '78 is a professor of petroleum geosciences at the National University of Singapore (NUS). He received his PhD in geophysics from MIT in 1978 under Toksoz, for work on seismic waves in porous rocks. He stayed on as principal research scientist and became the project leader of the borehole acoustics and logging consortium. After an accomplished career in industry (1996-2014), Cheng returned to academia and became a professor at NUS. He is a former member of the EAPS Visiting Committee at MIT and was awarded a Life Membership from the Society of Exploration Geophysicists in 2013. His research interests include acoustic, elastic, and tube waves in boreholes; rock physics; anisotropy; and fracture physics.