Learning decision boundaries for cone penetration test classification

Georg H. Erharter*, Simon Oberhollenzer, Anna Fankhauser, Roman Marte, Thomas Marcher

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


In geotechnical field investigations, cone penetration tests (CPT) are increasingly used for ground characterization of fine-grained soils. Test results are different parameters that are typically visualized in CPT based data interpretation charts. In this paper we propose a novel methodology which is based on supervised machine learning that permits a redefinition of the boundaries within these charts to account for unique soil conditions. We train ensembles of randomly generated artificial neural networks to classify six soil types based on a database of hundreds of CPT tests from Austria and Norway. After training we combine the multiple unique solutions for this classification problem and visualize the new decision boundaries in between the soil types. The generated boundaries between soil types are comprehensible and are a step towards automatically adjusted CPT interpretation charts for specific local conditions.

Original languageEnglish
Pages (from-to)489-503
Number of pages15
JournalComputer-Aided Civil and Infrastructure Engineering
Issue number4
Publication statusPublished - Apr 2021


  • CPT
  • Machine Learning
  • Supervised Learning
  • Soil Mechanics

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design
  • Computational Theory and Mathematics


Dive into the research topics of 'Learning decision boundaries for cone penetration test classification'. Together they form a unique fingerprint.

Cite this