Automatic identification of streamlined subglacial bedforms using machine learning: an open-source Python approach

This is a Preprint and has not been peer reviewed. This is version 1 of this Preprint.

Add a Comment

You must log in to post a comment.


There are no comments or no comments have been made public for this article.


Download Preprint


Ellianna Abrahams, Marion A. McKenzie , Fernando Pérez, Ryan Venturelli


Subglacial processes exert a major control on ice streaming. Constraining subglacial conditions thus allows for more accurate predictions of ice mass loss. Due to the difficulty in observing large‐scale conditions of the modern subglacial environment, we turn to geologic records of ice streaming in deglaciated environments. Morphometric values of streamlined subglacial bedforms provide valuable information about the relative speed, direction, and maturity of past ice streams and the relationship between ice streaming and subglacial erosion and deposition. However, man‐ ually identifying streamlined subglacial bedforms across deglaciated landscapes, sometimes in clusters of several thousand, is an arduous task with difficult‐to‐control sources of variability and human‐biased errors. This paper presents a new tool that utilizes a machine learning approach to automatically identify glacially derived streamlined features. Slope variations across a landscape, identified by Topographic Position Index, undergo analysis from a series of supervised machine learning models trained from over 600,000 data points identified across the deglaciated North‐ ern Hemisphere (McKenzie et al. 2022). A filtered dataset produced through the combination of scientifically driven preprocessing and statistical downsampling improved the robusticity of our ap‐ proach. After cross‐validation, we found that Random Forest detected the most true positives, up to 94.5% on a withheld test set, while an ensemble average of models provided the highest stability when applied within the range of applicable datasets. We build these models into an open‐source Python package, bedmap, and apply it to new data in the Green Bay Lobe region, finding the general ice flow direction and average streamlined subglacial bedform elongation with minimal effort. This type of open, reproducible machine learning analysis is at the leading edge of glacial geomorphol‐ ogy and will continue to improve with integration of newly acquired and previously collected data.



Geomorphology, Glaciology, Statistical Models


subglacial environment, machine learning, open science, Glaciology


Published: 2024-06-16 04:42

Last Updated: 2024-06-16 11:42


CC BY Attribution 4.0 International

Additional Metadata

Conflict of interest statement:

Data Availability (Reason not available):
In addition to the training dataset and Python codes for this tool made available through Zenodo and CryoCloud, a Jupyter Book is be‐ ing developed for step‐by‐step instructions on tool execution. The Zenodo‐published Jupyter Book will include chapters such as ”Upload‐ ing geomorphology data into Python” and ”Training a Random Forest tool”. The training dataset and TPI tool is available from McKenzie et al., 2022.