Embedding principles of MLOps at Solution Seeker

Published October 11th 2021, 07:51

MLOps revolves around operationalizing ML systems. It combines elements from multiple disciplines such as data science, DevOps and software development, and facilitates the machine learning journey from localhost to production.

Opening the front door from your desk

Published October 8th 2021, 11:03

BCG Acquires Stake in Solution Seeker—the Company

Brings AI Optimization to Upstream Oil and Gas

Published September 8th 2021, 03:42

Boston Consulting Group Strengthens Its Investment in AI in Oil and Gas by Joining the Oslo-Based AI Company

Get to know our summer interns

Published July 6th 2021, 01:48

Only a few weeks have passed since our six summer interns first showed up at the office. Already, the results are impressive and we can’t wait to see the final outcome! Before we reveal more about the projects, get to know each of our bright interns.

Solution Seeker granted funds to continue research of Transfer Learning methods for data-driven rate estimates

Published June 28th 2021, 09:30

The Norwegian Research Council recently awarded Solution Seeker funds for an Innovation Project. The objective is to obtain better well flow rate estimates by using the machine learning concept of transfer learning.

Meet our summer interns 2021

Published June 21st 2021, 03:28

The summer has finally announced its arrival and so have our six summer interns. We are excited for them to work with us on two tough but exciting projects.

Can we trust the data-driven VFMs?

Published April 23rd 2021, 06:08

A data-driven VFM presents an estimate of the flow rate, but how certain is really the model about this value? In a study performed on data-driven VFM modeling, we spent some time digging into calibration plots to assess the quality of the models.

Calibration plots - how confident is your model about itself?

Published April 9th 2021, 01:09

Calibration plots can be used to analyze probabilistic models. In short, the plot casts light upon how confident or uncertain a model is about its own predictions, and if we, as users of the model, can trust this uncertainty. Let us explain how.

Traditional data-driven VFMs have inherent challenges that make them unsuitable for widespread use across O&G fields

Published March 26th 2021, 02:00

This post presents our findings from a comprehensive study of data-driven VFM modeling. We looked at model performance and generalization, the impact of more sophisticated modeling methods and the effect of data quality vs. quantity.

Solution Seeker proud sponsor of successful applied AI conference

Published March 19th 2021, 02:00

The topic of this year's Women in Data Science (Oslo) was applied AI. Ten prominent tech experts across Norwegian industry gave lectures on how they are using artificial intelligence in their companies.

Latest journal entries