Long-Short Term Memory (LSTM) as a Machine Learning Algorithm for Seismic Inversion

Shang Huang, P Woźniakowska, Marcelo Guarido, Daniel O. Trad, David J. Emery

The CREWES Data Science Initiative presents the fourth lab of a series of four, focused on the solutions for seismic inversion using machine learning.

Geophysics in the Cloud was a competition with the goal to perform seismic inversion of rock atributes from seismic data with the use of well logs. It used open data (3D Poseidon from Australia) and the competitiors needed to perform inversions for P-Impedance, S-Impedance, and Density. Well logs with DTC, DTS and RHOB are used for training and evaluation (two blind wells). After the data analysis, pre-processing, and feature engineering (presented during labs 15 and 16), now it comes the modelling part. There are a large number of solutions to choose from. One of them is to use a U-Net deep learning model. This solution treats the seismic traces as 1-D images and uses a window od samples to perform local predictions. It has the advantage to consider each sample as dependent on its neighbours.

For this event, we are introducing two guest presenters: Shang Huang and Paulina Woźniakowska. They are both specialists in machine learning and worked together during the competition.

For this event, they will do a hands-on demonstration on how to use a LSTM model to perform seismic inversion. All in Python using the Tensorflow library.