Novi’s New Prediction Engine Accelerates Well Planning

Novi Labs (“Novi”) announces the release of Novi Prediction Engine™, a new self-service software capability that enables rapid modeling of oil & gas capital allocation scenarios in minutes. It was built to add efficiency and scale by simplifying the creation of “what if” scenarios that are key to reducing risks associated with maximizing return on capital and net asset value.

Novi Prediction Engine utilizes machine learning to automate resource intensive capital allocation scenarios while delivering more accurate forecasts of well performance based on a wide variety of inputs. It enables parallel testing of spacing, stacking and stimulation intensity scenarios. This optimizes capital allocation, asset value, and enables rapid analysis of acquisition and divestiture opportunities. The announcement was made at the SPE Hydraulic Fracturing Technology Conference (HFTC) taking place this week in The Woodlands, Texas. Media and other HFTC attendees are invited to visit Novi’s booth for more information about its latest product innovation. A video demonstration of Novi Prediction Engine is also available in the Resource Library section of the Novi website at www.novilabs.com/prediction-engine-release.

Since its inception, Novi’s cloud-based well planning solution has enabled engineering and planning teams to predict oil & gas recovery utilizing machine learning. Novi’s core platform is built on machine learning pipelines that leverage a variety of inputs, including Novi proprietary wells spacing, target formations, subsurface, fluids, proppant load and many others.

Output datasets from Novi Prediction Engine are stored in the Novi Cloud™, which supports direct integration with business intelligence platforms such as Spotfire, Tableau, or PowerBI. In addition, Novi Data™ provides insights that support each prediction as part of Novi’s initiative to bring transparency to machine learning and predictive analytics.

“Our new Prediction Engine massively increases operational efficiency when it comes to well planning, enabling our customers to rapidly generate accurate predictions that influence final well design and capital allocation,” said Scott Sherwood, Novi’s CEO. “By tapping the power of machine learning, Novi allows engineering and planning teams to test critical assumptions about drilling and completion and get instant insight into the materials, designs, and best practices that yield optimal recovery and cost performance,” he said.

For more information about Novi’s Prediction Engine, please visit booth #24 at SPE HFTC this week or watch a short demonstration by visiting www.novilabs.com/prediction-engine-release.

Latest News

Exhibition / Event

Novi Attends NAPE 2024!

We’re thrilled to be part of this year’s NAPE event, and it’s particularly special as we unveil innovative analytics solutions using our proprietary production data. ...
Read More →
glossary(don't touch)

What is {{mpg_keyword}}? | Novi Labs

Oil & Gas Glossary {{mpg_keyword}}​ Confused by multitude of oil & gas data and analytics terms? Get easy-to-understand definitions in our glossary. Other terms What ...
Read More →
Release note

Novi Labs Releases Novi Data Network (NDN), Leveraging Proprietary Oil and Gas Data for AI Driven Well Forecasting Models

We are pleased to announce the release of Novi Data Network (NDN). NDN allows oil & gas operators to collectively pool their production and completion ...
Read More →

News, trends and data for the US upstream industry

Novi Energy Newsletter

Sign up today for free and get a weekly email with news and insights on important developments in one or two of the major tight oil & gas basins.

Name(Required)
This field is for validation purposes and should be left unchanged.

Meet Novi Labs' knowledgeable experts.

Invite to Speak

Our team of experts is passionate about sharing valuable insights on US energy. Please provide us some information about your event, and we will get back to you as soon as we can

Date
This field is for validation purposes and should be left unchanged.