SR-01Frontier
Smart Proxy Reservoir Simulation
A learned stand-in for the full reservoir simulator that answers in seconds instead of hours, so an engineer can test fifty scenarios instead of three.
Subsurface & Reservoir IntelligenceAIDomain
SR-02FrontierWave 3AIDomain
Automated History Matching
In one sentence
Tunes the reservoir model until it reproduces what the field actually produced, automatically and with the uncertainty kept rather than discarded.
The problem
Manual history matching takes three to six months per field and produces a single "matched" model whose uncertainty has been argued away rather than quantified. Decisions are then made as if that one model were the truth.
How it works
An ensemble smoother with multiple data assimilation updates the property ensemble against production history, keeping a family of matched models rather than collapsing to one. Parameter groups are constrained to geologically plausible ranges agreed with the geomodeller before the run.
Data required
- Simulation model with a defined uncertain-parameter set
- Clean production and injection history by well, with allocation quality flagged
- Pressure surveys and well test results with dates
- Geological constraints on each uncertain parameter
What you get
- Ensemble of matched models with posterior parameter distributions
- Match quality by well and by phase, with the poorly matched wells named
- Forecast bands rather than a single deterministic forecast
What it cannot do
The method assimilates the data it is given, so allocation error in the production history becomes a property of the matched model. In fields with back-allocated rates and no well-test discipline the result is a model that matches wrong numbers precisely. We run a data-quality gate first and have refused this work where the gate failed.
Every capability page states a real limitation. If a vendor cannot tell you where their product stops, you are not being told the truth about where it starts.
Related capabilities
- SR-11Intermediate
Forecasting with Uncertainty
Produces P10, P50 and P90 production forecasts whose spread is calculated, not chosen to look reasonable.
Subsurface & Reservoir IntelligenceAI - DF-07Foundational
Automated Data Quality Control
Continuously checks incoming data for stuck sensors, impossible values, missing periods and broken units, and reports the field’s data health as a number.
Data FoundationITAI - PR-11Intermediate
Waterflood & Produced Water Management
Works out which injector is actually supporting which producer, and where the injected water is being wasted.
Production & Artificial LiftAIDomain - SR-05Frontier
Generative Inter-Well Modeling
Fills the rock between wells with geologically plausible detail instead of a smooth interpolation that no outcrop ever looked like.
Subsurface & Reservoir IntelligenceAI