OAG Analytics demystifies the subsurface and improves the
predictability of field development planning.
Add OAG to Your Well Planning Workflows
Proprietary Reservoir Depletion and Well Interference Algorithms
Planning New Drilling Units
Planning a new drilling unit requires evaluating how localized geology and geophysics interact with well designs. Machine learning models trained with geo, well, and production data are faster than type curves for estimating the production of wells that are not within hundreds of feet of other wells. Unfortunately, drilling wells far enough apart to isolate them from the effects of depletion and interference does not maximize drilling unit economics.
Oil, gas, and water production in a new drilling unit is a complex function of geo properties, well designs, well spacing, and drill timing. Modeling well spacing and timing requires combining oil & gas-specific algorithms with machine learning to create models that understand enough about reservoir depletion and well interference to improve the predictability of complex full-stack development.
OAG’s Well Planning software learns new insights from rock, completion, location, and production data to improve:
Well spacing and sequencing
Stage and cluster spacing
Proppant and fluid loading
Offset production volumes
Planning Infill Drilling Units
Adding more wells to drilling units that already have wells, i.e. infill, adds additional complexity, as the impact that existing wells (parents) have on new wells (children) changes as a function of time and space between wells.
OAG’s proprietary well interference algorithms combine with machine learning to train models that improve the predictability of frac hits between different parent/child well pairs. OAG also provides web-based software for SMEs to update frac hit labels, accelerating learning by facilitating SME-computer collaboration. The OAG Frac Hit UI displays data like daily production, high frequency SCADA production, pressure, frac truck data, well locations, geo data, and type curve areas.
OAG's Infill Drilling Unit solutions improve the predictability of:
Offset production impact of frac hits
Add OAG to Your Subsurface Workflows
Computational Geometry to Extract New Signals from Your Maps
Demystify the Subsurface
Geoscience is uniquely poised to benefit from machine learning. Much of the industry’s “big data” is captured in seismic and well logs, and some level of interpretation or qualitative evaluation is usually necessary. Machine learning evaluates large data sets and helps geoscientists pair their qualitative interpretations with automated and quantitative workflows to better assess risk.
Through automation and quantification, operators are improving consistency; reducing interpretation time; and providing higher fidelity geologic and geophysical inputs to critical cross-disciplinary operations such as well spacing, completions optimization, and landing zone optimization.
Improve existing maps
Automate basin-wide mapping
Predict core properties from logs
Identify facies from logs
Missing log prediction
It All Begins With the Data
OAG Data Manager
During upstream operations, millions of data points are generated and stored in an array of database instances that are disconnected and difficult to access. Data Manager simplifies the process of preparing and managing your complex data portfolio and enables self-service access for your entire team.
- Organize all data types
- Combine public, subscription, and proprietary data
- Normalize data stored in multiple formats
- Create a data set in minutes using a point and click interface
- Seamlessly integrate with data visualization tools like TIBCO Spotfire