Project using AI for 4D seismic kickoffs
At the end of last year LTrace was selected at a contest promoted by PETROBRAS and SEBRAE called “Petrobras connections for innovation – Startup module”
The project entitled “Deep learning for 4D seismic assimilation on reservoir models” proposes the use of convolutional neural networks for improving the level of quantitative information assimilated from 4D seismic data on history matching algorithms. The project has started this month with a total duration of 12 months. In this brief period the team hopes to deliver a proof of concept as a Petrel plugin for G&G users of Petrobras to test and give us feedback more promptly. We will be using the Ocean for Petrel framework to develop the plugin, integrating it with a Petrobras in-house software solution for history matching called BR-Kalman.
ai, history matching, kalman filter, machine learning, neural networks, ocean plugin, petrel, R&D, reservoir engineering, seismic