proteus simulation and optimization platform
Physics Rectified Optimization of
Timeframe, Economics, U ncertainty & Safety
History Matching (HM)
Accurate history matching is mission critical to having confidence in your model. Traditionally, history matching was completed manually, and extremely slowly. In recent years, software providers have released tools to aid in the process, but these have resulted in their own challenges, often relying on black box simulations, and very high computational demands.
PROTEUS-HM utilizes a proprietary neural network and modeling methodology to provide the next generation in history matching results and quality. Our platform is able to ingest historical data, and automatically perform history matching optimization. To get into the finer details, our neural network is fully differentiable, and completely transparent, NOT A BLACK BOX. This enables speedups and efficiency improvements by up to 10,000x, allowing for an incredibly effective global optimization.
The resulting history-matched model provides an unprecedented level of confidence, greatly enhancing the trust in subsequent Field Development Planning.
Field Development Plan (FDP)
A field development plan (FDP) determines the production strategy, specifying, among other things, the location and drilling schedule of wells. Reservoir flow simulators are traditionally used to forecast field production rates for any user-set production strategy and petrophysical properties. This allows the estimation of the economic value of an FDP candidate.
With that in mind, traditional simulators are SLOW. Simulations can take days, and full workflows can take weeks. Decisions and iterations drag on, and in the end decisions must be made on less than optimal information. Compute costs are also prohibitive for very large models (1M+ cells). The impacts of such time and compute limitations prevent the highly granular understanding necessary to achieve true optimization.
PROTEUS-FDP delivers results thousands of times faster than conventional simulators. The bottleneck of waiting on reservoir modeling is eliminated. Instead of data entry errors costing hours or possibly days, the model can simply be corrected and run again instantaneously. Instead of looking at 100 potential options for a field development plan, millions of options can be analyzed, massively enhancing solution optimization, and reducing uncertainty.
Real Time Optimization (RTO)
The aggressive pursuit of intelligent digital oil and gas fields has resulted in recent technologies that target the goal of continuous asset optimization. While these technologies have enabled substantial improvements, temporal limitations prevent many optimizations from being performed in real time.
PROTEUS-RTO builds upon our core technology, enabling ingestion of real-time data from operating fields. This flow of data from the field enables us to constantly refine and optimize history matching in real-time, including interaction effects between multiple injection and producer wells in a given field. This is optimization of well control on a level not previously seen. The efficiency and speed of our platform untethers decision makers from prior constraints, enabling them to analyze poor performers, and depleted wells that previously would not have been worth the effort, unlocking enhanced production and return on investment.
CO2 Sequestration
One of the main challenges for the energy industry is greatly reducing their carbon footprint and overall CO2 emissions. This transformation will require the adoption of new technologies to reduce GHG emissions in the following years. In this regard, CO2 storage/sequestration in saline aquifers or reservoir basins is gaining a lot of interest as one of the primary strategies to reduce CO2 emissions.
However, CO2 storage is not an easy task. Injection of CO2 into deep saline aquifers is an important emerging field of reservoir geoscience, involving different dynamic processes from hydrocarbon reservoir modelling. Specifically, one of the most important challenges in CO2 sequestration is obtaining an accurate model of the reservoir to allow safe sequestration without risk of leaks or earthquakes as well as optimizing the sequestration to minimize these risks.
Current reservoir simulators present many limitations to simulate this process. 1) Due to high computational demand, current reservoir simulations of CO2 storage are limited to a small sector of the reservoir. 2) Coupling geomechanics and simulations of porous flow requires new generations of solvers that allow the simulation of the process at a high resolution to predict the forming of fractures and microseismics events 3) Current simulations do not allow the application of optimization and uncertainty techniques necessary to effectively achieve these goals.
All these limitations can be addressed with our current physics-informed AI approach. PROTEUS-CO2 is coming soon.
Renewable Energy (CFD)
Wind energy has received increasing attention in recent years due to its sustainability and geographically wide availability. The efficiency of wind farm utilisation highly depends on the performance of wind turbines, features such as turbine position and design are crucial to maximize the energy production. In order to optimize the wind farm plan and increase the wind turbine performance is necessary two different elements: 1) Simulation tools that can predict the future behavior and states of the wind turbine 2) optimization tools that can max/min multiple objectives function such as annual energy production, the cost of energy or the blade mass.
Planning and design of wind turbines and wind turbine fields is taken to an entirely new level through PROTEUS-WND (coming soon). Large scale simulations are able to include multiple turbines as well as their interaction effects, providing results that allow for optimization of aerofoil design and enhanced turbine design for new fields. Improved efficiency of design and planning will have multiple second and third order impacts. Design and efficiency improvements will result in enhanced uptake and implementation of new wind-turbine technology, further enhancing wind-energy competitiveness.
Real time analysis and optimization becomes possible. The ability to consider more factors, enables much more accurate analysis. Through inclusion of interaction effects, more simulations, and better accounting for probabilistic predictions of weather, real-time energy planning is dramatically enhanced. This allows for better energy distribution planning, and reduced costs of energy.