About the creator

Andy McDonald

I work across geoscience, software and machine learning, building practical tools for subsurface data, interpretation and decision making.

Background

I have nearly 20 years of experience working with subsurface data in the oil and gas industry, across technical, software and product-facing roles. My work has included building industry software modules, developing applied machine learning workflows for geoscience problems, and creating technical training material for geoscientists.

I have delivered conference workshops, written long-form technical articles and published open notebooks on Python and subsurface data analysis. I also write independently through Subsurface Syntax, on practical ways of working with geological data.

Why Fit Lab

Machine learning on well logs is easy to start and easy to get wrong. Most tutorials show the code and the score; few show what the algorithm is doing to the samples, or why a score of 98% can mean very little on the next well. Fit Lab shows both, on wells where the truth is known, and asks you to try each job yourself before the algorithm does.

It joins Pore Lab, Bore Lab and Probe Lab in the Labs series, and takes its rock physics from Probe Lab. It's the first to work in two dimensions: paper and ink rather than 3D.

Inspired by

The Labs series was inspired by Ryan Sael's The Plane of Focus, an interactive lens lab that explains camera focus by letting you turn the focus ring and watch the sharp plane move through a scene. It showed how much a well-lit, hands-on model can teach.

Find me

Rights

© 2026 Andy McDonald. All rights reserved. The code, figures, text and synthetic wells in Fit Lab may not be copied, modified, republished or reused without written permission. You are welcome to link to it.

The real wells come from the FORCE 2020 dataset (Bormann et al., 2020), used under CC BY 4.0 with the log data under NLOD 2.0; the fonts are Source Serif 4, Space Grotesk and JetBrains Mono, used under the SIL Open Font License. See the third-party notices and the data.

The wells in Fit Lab are generated from simplified teaching models, not real tool responses, except the FORCE 2020 wells in each chapter's real-wells section.