Subsurface Syntax

Subsurface Syntax

Random Forest for Lithology Classification From Well Log Data

Classifying the Subsurface With Machine Learning

Andy McDonald's avatar
Andy McDonald
Aug 20, 2022
∙ Paid

Machine Learning | Petrophysics

Classifying the Subsurface With Machine Learning

Photo by Nejc Košir: https://www.pexels.com/photo/green-leafed-tree-338936/

Random Forest is a very popular machine learning algorithm that can be used for both classification, where we are trying to predict a category or class, and regression, where we are trying to predict a continuous variable.

Within petrophysics and geoscience, we can use this algorithm for predicting lithologies from well log measurements or predicting continuous logging curves such as a continuous permeability from core measurements.

Within this article, we are going to focus on the application of Random Forest to the prediction of lithologies from well log measurements. But first, let us have a look at how Random Forest works.

Introduction to Random Forest for Classification

At a very high level, a random forest is essentially a collection of decision trees. These are very simple and intuitive to understand, and we often use them in day-…

Keep reading with a 7-day free trial

Subscribe to Subsurface Syntax to keep reading this post and get 7 days of free access to the full post archives.

Already a paid subscriber? Sign in
© 2026 Andy McDonald · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture