Prediction and Optimization with World Leading Performance
AI for physics: Complete Reservoir Simulations in Seconds
Benefits of Physics Informed Deep Learning
We bring industry leading technology to Oil and Gas Exploration and Production
Real Time Reservoir Simulation and Optimization
Complete reservoir simulations in seconds. Up to 10,000x faster than conventional simulators.
Highly Accurate Simulation
Enjoy up to a 1000x improvement to simulation resolution, with seismic (cm) level cell sizing.
Increased production, reduced capital expenditure, and no additional infrastructure required. Up to 20% improvements in project NPV.
Highly Efficient Simulation and Optimization
Save on cloud resources. With near instantaneous, highly accurate results, iterate to your heart's content.
Simulation and Optimization Platform: PROTEUS
Our PROTEUS platform is a workflow game changer. We solve a broad range of novel challenges with our highly flexible technology. Field Development Planning, History Matching, and Optimization just to name a few. New modules are constantly being developed.
Physics Informed Simulation Research
Research in deep reinforcement learning
Many of the most challenging optimization problems cannot be solved with conventional approaches. The problems facing the energy industry are more complex and dynamic than ever before. Our team has developed unique, deep reinforcement learning algorithms which have been used for real-time optimization and planning across multiple domains, and have yielded unprecedented results.
Physics-Informed Deep Learning to solve differential equations
Informing our machine learning models with what we know about physics can make them learn faster and better. We also in many cases know some, but not all, of the specific dynamics of a class of systems. Learning directly from scientific knowledge quickly guides the algorithm towards solutions that preserve known physics fundamentals, even when data is sparse.
While other platforms use physics as constraints, we are actually solving the partial differential equations. Full simulation describes pressure, saturation, velocity, and more, at every node.