Best-in-class A.I. platform for Earth Modeling
QEarth delivers real-time earth modeling to enable the automation of critical geoscience workflows and drilling operations.
Retrieve Critical Subsurface Insights in Real-time
Virtually any property that can be logged or measured in a wellbore can be delivered as a property volume through QEarth. The true power of QEarth comes from the closed-loop automation that allows it to transform drilling data and logged rock properties into contextual earth models for drilling and geoscience applications.
A Solution Aligned with your Organization's Goals
QEarth is the culmination of our different technologies at Quantico. It ties together different data driven subsurface products to bring a complete reservoir characterization platform to our customers.
Informed decisions about the reservoir can be made in real-time.
Validated by most of the world’s
largest oil and gas producers.
Modern User Experience
A thoughtful modern user interface designed with future generations in mind.
Earth modeling that takes days rather than months saves more than just time; it represents significant carbon cost savings.
Data drives the process, not human subjectivity. The experts can spend more time on the hypothesis testing, not the button clicking.
Ease of training, reduction of human error, and results in days all culminate in significant cost savings.
Tackling a Variety of Drilling and Subsurface Challenges
When deploying QEarth within your organization you will have the power to tackle a great variety of subsurface challenges. It uses machine learning to construct a high resolution earth model of virtually any property including pore pressures, fracture gradients, unconfined compressive strength. Using drilling data, QEarth updates the earth model in real-time – autonomously without human intervention.
High Fidelity, Low Cost Earth Models - On Demand
Our earth modeling solution puts real-time subsurface insights in the hands of the entire oilfield. Geoscientists and engineers can resolve entire volumes of earth properties with best-in-class machine learning workflows and data handling.
Effective & Total Porosity
The results of the study were replicated in this movie that exemplifies the real-time capabilities of QEarth. This closed loop experiment takes in logged rock properties and updates an entire property volume in real-time.
Frequently asked questions
What is the essential input data to QEarth?
Seismic (stack and angle stack reflectivities and derived attributes) and interpreted surfaces. Well logs and well tops for training.
How does your ML inversion treat the seismic wavelet?
We do not explicitly extract the seismic wavelet. We treat the seismic trace as a time (or depth) series and sample it at a resolution that approaches log scale.
What properties can be predicted with QEarth?
Virtually any property that is logged or measured in the wellbore, e.g., velocities, derivative attributes, Gamma Ray, Resistivity, Density, Stresses, TOC, Brittleness, Pore Pressure, etc. Also drilling measurements such as UCS, wellbore stability, WOB, etc.
How much input/decision making is typically required by a user in QEarth compared to conventional methods?
Much of the QEarth process is automated. In addition, time consuming tasks such as rock physics modeling, wavelet extraction and low frequency model building are not performed in this data-driven approach. Hence the dramatic reduction in time-to-solution.
Where has QEarth been applied (a) conventional: clastics & carbonates (b) Unconventionals and what were the results?
A) Sub-salt GOM and pre-salt Brazil, offshore Malaysia, offshore onshore Alaska, onshore Middle East, offshore Oman, onshore Colombia.
B) Several in the Permian Basin and Eagle Ford in Texas.
SCOOP/STACK play in Oklahoma.Results have mostly been good to excellent. Only one was disappointing due to poor well availability and imaging issues (poor seismic-to-well tie)
Do you have to input a low frequency trend or depth dependency?
The low frequency trend/depth dependency is explicitly present in the input log data and is "learned" by the neural network during the training phase.
How do you address uncertainty in your reservoir property predictions?
We use a process called Bagging (Bootstrap aggregation) where the algorithm randomly selects 20% - 30% of the input data and uses it to verify simulations. We also randomly withhold wells from the training set in a round-robin fashion. This is called Grid Search with K-Fold cross-validation.
What type of neural network do you use? Is it a deep learning algorithm
There’s generally not enough data to justify the use of a Deep Learning neural network so we generally use a simple ANN. Where the “secret sauce” comes into play is how one sets up the NN to reference the data properly. We don’t just look at one data point at the trace at a particular depth – we look at a user-specified number of samples within a sliding/overlapping reference window.
What kind of seismic attributes do you put into QEarth? Is it just amplitude or are there other key attributes?
We are quite flexible in terms of the input seismic attributes. Effectively we can use the same attributes as a standard seismic inversion, but we are not limited to amplitude data. We can even input AVO attributes and conventional inversion attributes. One key point to make is that we can explicitly invert for properties rather than deriving them mathematically from Ip, Is, and Density. This is especially important when one considers we can use QEarth to invert for drilling dynamics data, such as weight on bit, pore pressure, fracture gradient, wellbore stability and UCS, etc.
How much does it cost to build a hi-res earth mode with QEarth?
If you provide # of wells with full log suites, areal extent of 3D seismic and number of properties you wish to have simulated, we can provide indicative pricing.
Submit a Technical Presentation Request if interested in learning more
Are there any limits to the size of the seismic data volume size and the number of wells?
No. It stands to reason that an inversion model would benefit from a larger number of wells, but over-training may happen. Depending on the size of the volumes and attributes of the data varying populations of wells are used.
How will QEarth handle poor well control or poorly sampled geology?
Neural networks are not great extrapolators but Quantico will conduct extensive analysis of well control prior to kick-starting a project. Before a project starts, we will communicate concerns about poorly sampled areas of a volume and determine what KPIs are feasible given the data available.
© Quantico Energy Solutions 2020