Official Petro.ai Blog

Thanksgiving Toast to the Believers of Shale

Thanksgiving Toast to the Believers of Shale

Troy Ruths
A simple post of gratitude to our customers and to the industry.
Empower Your Team with Multi-variate Thinking

Empower Your Team with Multi-variate Thinking

While some productivity drivers in a tight reservoir are observable and easily measured, others require multi-variate regressions and physics-driven feature engineering.

Troy Ruths
Three Executive Strategies for Pushing Back the Inventory Wall

Three Executive Strategies for Pushing Back the Inventory Wall

The shale inventory wall is a real challenge for our industry and has made the news circuit this past week.

Troy Ruths
Improve DSU Design Decision Making with Petro.ai Features

Improve DSU Design Decision Making with Petro.ai Features

Machine Learning (ML) models are critical tools in understanding productivity drivers and predicting DSU performance, but including too many features in your ML models reduces their impact on explain-ability and generalize-ability.

Troy Ruths
Feature Exploration in the DSU Design Service: Partial Dependency Plots

Feature Exploration in the DSU Design Service: Partial Dependency Plots

Kyle LaMotta, VP of Analytics explains, “The partial dependency plots (PDP) are one of the model diagnostics that we’ll use in every DSU Design Service analysis. The PDPs are a way to visualize how a feature is contributing to a prediction.

Rosemary Jackson
Breaking the Accuracy Barrier:  Feature Exploration in the Petro.ai DSU Design Service

Breaking the Accuracy Barrier: Feature Exploration in the Petro.ai DSU Design Service

Feature exploration is a critical part of the Petro.ai DSU Design Service (DSUDS) model development. Recommendation reports are presented in live, interactive meetings where the client’s asset team and the Petro.ai team discuss the features that need to be included and interpreted in the model.

Rosemary Jackson
Public Data and Baseline Model Development

Public Data and Baseline Model Development

“We can build models with only public data,” Kyle LaMotta, VP of Analytics explains. “There’s enough information reported in the public data to create predictions. While that information is limited, we can build a model using features like total proppant, total fluid, lateral length, latitude, and longitude. That’s really the most information that we can get out of public data.

Rosemary Jackson
PETRO
TEXAS
114 Main Street Ste. 400
Houston, TX 77002
CANADA
4-5609 Avenue du Parc
Montreal QC, H2V 4S8