Reduce subsurface uncertainty in seismic reservoir characterization studies by predicting rock properties in 3D using machine learning. Our AI algorithms use ensemble learning and neural network technology to predict acoustic, elastic, and petrophysical properties from seismic data.
Geosolutions...
TROID Classification
Using well data and 3D rock properties, a spatial distribution of facies can be estimated using classification algorithms backed by artificial intelligence.
Seismic Inversion
The use of inversion methods allows for 1D borehole measurements to be parameterized into 3D space by integrating the well and the seismic data. To some degree, the inversion output simulates wireline measurements being recorded at each trace in a seismic survey without the need to drill expensive wells. This is possible by analyzing the variation of seismic amplitude with incident angle (AVO and/or azimuth) at a geological interface, which contains information about the rock and fluid properties within the layers.
TROID Log Prediction
Having sonic and shear sonic measurements at all wells is central to mapping the lateral extent of a reservoir in seismic reservoir characterization studies. Machine Learning may be used to help reduce the cost of a characterization campaign by eliminating the need to acquire these logs at every well.
Seismic Conditioning
The quality of migrated gathers is central to seismic inversion. The objective of seismic conditioning is to ensure amplitude preservation while eliminating the post-processing residual effects of noise and multiples.
Courses
Multi-Physics provides technical and practical training and professional development services for the E&P industry (http://www.nexttraining.net). The delivery method can be either as a traditional course or a more hands-on approach.