The energy industry is transitioning to low-carbon solutions to achieve net-zero emissions while meeting increasing global demand. New technologies are driving digital transformation to support the transition to clean energy and operational efficiencies.
Computational Geosciences is an industry leader in developing automated solutions to address upstream challenges spanning discovery, appraisal, development, operational, and closure phases.
For more information and detailed case studies, please click on the links below.
"Computational Geosciences has provided electromagnetic modeling, both during the survey design and ultimately the data inversion, for Zonge’s mining, energy, and environmental customers. Christoph and Mike have both been excellent partners in providing the outstanding inversion products to those clients."
President, Managing Geophysicist
Computational Geosciences has developed and collaborated to deploy the industry’s first and only real-time 3D inversion solution for resistivity logging-while-drilling (LWD) data, significantly optimizing well placement and well completion designs to maximize reservoir productivity.
Computational Geoscience’s automatic classification solutions enables lithological classification of seismic images, significantly improving seismic interpretation productivity.
Computational Geoscience has developed and deployed 3D electromagnetic imaging-through-casing. By modeling the entire complexity of the completions infrastructure, subtle formation responses can be inverted subject to seismic and petrophysical constraints for 4D fluid substitution and stimulation-induced changes within the reservoir that are otherwise indiscernible from seismic methods, accelerating the engineered learning curve for completion optimization.
Monitoring of fluid substitution within reservoirs, whether for enhanced oil recovery (EOR) or carbon capture and storage (CCS), necessitates an intricate coupling between geophysical inversions and flow simulations. Computational Geoscience’s joint 4D inversion of geophysical and flow data yields fluid substitution insight not discernable by either geophysical inversion or flow simulations alone.
Computational Geosciences has developed a neural-network-based seismic stratigraphy solution to rapidly and reliably detect and simultaneously track multiple seismic horizons, even in areas of low image resolution, significantly improving structural interpretation productivity.