06 Nov 2023
 | 06 Nov 2023
Status: this preprint is open for discussion.

A machine learning approach to the geomorphometric detection of ribbed moraines in Norway

Thomas James Barnes, Thomas Vikhamar Schuler, Simon Filhol, and Karianne Staalesen Lilleøren

Abstract. Machine learning is a powerful yet underutilised tool in geomorphology, commonly used for image–based pattern recognition. Analysing new high–resolution (1–10 m) elevation datasets, we investigate its usefulness for detecting discrete geomorphological features. This study develops a machine learning–based method for identifying ribbed moraines in digital elevation data and progresses to test its performance versus time consuming, manual methods. Ribbed moraines share geomorphometric characteristics with other glacial landforms, hence represent a valuable test of our new methodology in terms of differentiating between similar features, and wider for detection of landforms with similar characteristics. Furthermore, mapping ribbed moraines may provide valuable indications of their origin, a topic of debate within glacial geomorphology. To automatically detect ribbed moraines, we extract simple morphometrics from high–resolution digital elevation model data and mask regions where ribbed moraines are unlikely to form. We then test several machine learning algorithms before examining the best performer (K–means clustering) on three study areas in Norway of 15 km2. Our results demonstrate balanced accuracy of 65–75 % when validating versus ground–truth. The performance depends on the availability of high–resolution elevation data in Norway, needed to resolve the spatial scale of the target (10–100 m). We find the method effective at detecting both fields of ribbed moraines as well as individual ribbed moraines. We propose pathways for future implementation of this method on a large–scale and for increasing the detail of information gained about detected landforms. In conclusion, we demonstrate K–means clustering as a promising method for detecting ribbed moraines, with great potential to reduce the time needed to produce landform maps.

Thomas James Barnes et al.

Status: open (until 28 Dec 2023)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Thomas James Barnes et al.

Data sets

Aeteia/Ribbed-Moraine T. J. Barnes and S. Filhol

Model code and software

Aeteia/Ribbed-Moraine T. J. Barnes and S. Filhol

Thomas James Barnes et al.


Total article views: 92 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
65 24 3 92 1 1
  • HTML: 65
  • PDF: 24
  • XML: 3
  • Total: 92
  • BibTeX: 1
  • EndNote: 1
Views and downloads (calculated since 06 Nov 2023)
Cumulative views and downloads (calculated since 06 Nov 2023)

Viewed (geographical distribution)

Total article views: 91 (including HTML, PDF, and XML) Thereof 91 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 29 Nov 2023
Short summary
In this paper we use machine learning to automatically outline landforms based on their characteristics. We test several methods to identify the most accurate, and then proceed to develop the most accurate to improve its accuracy further. We manage to outline landforms with 65–75 % accuracy, at a resolution of 10 metres, thanks to high-quality/-resolution elevation data. We find that it is possible to run this method at a country-scale to quickly produce landform inventories for future studies.