DF-02Foundational
Structured Extraction from Reports
Pulls the numbers out of the reports — depths, rates, pressures, volumes, dates — and puts them into a database with a link back to the page they came from.
Data FoundationAIDomain
SR-13FoundationalWave 2DomainAI
PVT Modeling & EOS Tuning
In one sentence
Extracts fluid study data from decades of laboratory reports and tunes the equation of state against all of it, not against the one report someone had to hand.
The problem
PVT reports live as scanned PDFs in a cupboard. Simulation studies typically use one or two of them because finding and digitising the rest is a week of manual work, so reservoir-wide fluid variation is ignored.
How it works
Laboratory reports are digitised through the extraction pipeline into a structured PVT repository — CCE, DL, separator tests, compositions. The equation of state is then regressed against the full set with consistency checks between samples, and samples that disagree with their neighbours are flagged for review rather than averaged away.
Data required
- Historical PVT laboratory reports, scanned or digital
- Sampling conditions and sample validity notes
- Reservoir temperature and pressure at the sample depth
- Field production GOR history for cross-checking
What you get
- Structured PVT database with sample metadata and quality flags
- Tuned EOS model with regression report and match quality per experiment
- Fluid property maps showing compositional variation across the field
What it cannot do
Sample validity is the binding constraint, not the tuning. A large share of legacy samples were taken under conditions that make them unrepresentative, and no amount of regression fixes a bad sample. The system flags suspect samples and the honest outcome in several fields has been that a new sampling campaign is required.
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-09Foundational
EOR Method Screening
Rules out the EOR methods that cannot work in this reservoir before anyone spends a year simulating them.
Subsurface & Reservoir IntelligenceDomainAI - PR-06Intermediate
Virtual Flow Metering
Estimates each well’s oil, water and gas rate continuously from pressure and temperature, between the physical tests.
Production & Artificial LiftAIDomain - PR-08Intermediate
Flow Assurance Prediction
Predicts where wax, hydrate, scale or slugging will form in the flowline before the line blocks.
Production & Artificial LiftAIDomain - PR-13Foundational
Automated Nodal Analysis
Runs the inflow-outflow calculation for every well in the field on a schedule, instead of for a few wells when someone has time.
Production & Artificial LiftDomain