top of page

Case Study

Cross Border Machine Learning Project to Predict Hydrocarbon Pay

In mature basins most of the assets, specifically those easy-to-reach, have been exploited with reserves running low and existing fields are nearing the end of their lifetimes. Additionally, exploration, development and production costs in the North Sea are often high relative to other basins throughout the world. Identifying missed pay zones amongst thousands of drilled wells in a mature basin is a cost-effective approach and may well define a new era of exploration activities.

Earth Science Analytics were selected by the Norwegian Petroleum Directorate and the Oil and Gas Technology Centre to deliver the first-ever  cross border Machine Learning project

The objective was to predict oil/gas intervals amongst thousands of wells on a basin-scale leveraging cloud-native bud data analytics and Machine Learning technologies.

Operators from the UK and Norway donated over 30,000 kilometres of wireline data which was used to predict missing CPI curves and identify over 400 exploration opportunities.

An Exploration Workflow Catalyst
A typical exploration team can deal with 20% of the available data before they must make a drill decision. Therefore, we tend to focus efforts on the best quality or most well-known pay zones, and miss out on those 'diamonds in the rough'.

A collaborative cloud environment allows you to bring new insights to old concepts, capture expertise and explore with more agility.

Thanks to the 'on demand' access to computers via the cloud we could generate bad hole and QC flags in moments and use semi-automated tools to edit wells at both single and multi-well scales. The end result was a   databank built of 70 different types of data, spanning 90 million depth indexes.

From here we used our Wells tool to predict missing logs and then had proven oil finders review the results to make sure we had realistic predictions.

The Advent of a New Era for Exploration
By giving our exploration team the tools and data they needed in one place, we allowed them to take a second look at the subsurface

Using standard techniques for identifying and ranking pay zones, we found over 400 candidates that could be worth a second look.

These include misreported discoveries, new ideas in old areas and pay zones that were revealed by increasing the data coverage.

All of this information is available to geoscientists to slice and dice as they see fit via EarthNET Insight - meaning you can find your next discovery at the click of a button.

bottom of page