Operators of varying sizes all over the world have leveraged Tachyus across 50K+ wells to achieve up to a 20% increase in production and up to a 40% decrease in injection cost for waterfloods, steamfloods and miscible gas injection processes
Proven Technology used Worldwide
Physics + Machine Learning
Tachyus' Data Physics models are machine learning models that honor reservoir physics like traditional reservoir simulators, but are orders of magnitude faster
Build and validate predictive models in a matter of days that match all your historical production and injection data
Fast Model Creation
Fast What-If Analysis
Run what-if scenarios like the impact of changing injection rates, well conversions, infill well drilling, etc. in a matter of minutes
Run multi objective optimization to optimize injection rates, producer to injector conversions, etc. against many objectives like oil production, NPV, etc. in a few hours
Get an ensemble of models that all match your historical data to account for uncertainty and measurement errors
Understand your field through estimates of connectivity between wells, spatial variation of reservoir quality, and distributions of reservoir properties
Unique Reservoir Insights
Pan American Energy, a joint venture between BP and a local Argentinian company, used Aqueon to optimize the very large and complex Zorro field, and achieved a production increase of over 15%. The results have been published in the ADIPEC.
ConocoPhillips, one of the largest oil and gas operators, has added Aqueon to its global reservoir engineering workflows to advance physics-driven data analytics solutions and support waterflood management and optimization.
Denbury, a leader in CO2 EOR, has used Aqueon for operational management and optimization of multiple waterfloods. The results from these implementations have been recently presented at the EAGE Annual Conference.
In traditional reservoir management, various types of predictive models have been applied over the years for quantitative decision making. Such models range from the very simple analytical models (type-curves, etc.) to the very complex reservoir simulation models. Simulation models attempt to model detailed behavior of reservoir physics and integrate all kinds of measured data. However, many issues such as the significant time and effort required to build and calibrate these models, computational complexity, etc. generally make their practical application difficult.
Tachyus’ Data Physics is the amalgamation of the state-of-the-art in machine learning and the same underlying physics present in reservoir simulators. These models can be created as efficiently as machine learning models, integrate all kinds of data, and can be evaluated orders of magnitude faster than full scale simulation models, and since they include similar underlying physics as simulators, they have long term predictive capacity. The Data Physics based waterflood, gas injection, WAG, CO2 flood and steamflood management workflows are very fast and users can go from data preparation and modeling to decisions in a matter of days. Additionally, the models can be quickly updated with new data so that they always remain operationally useful.