Numerical characterization of surface heave associated with horizontal directional drilling

Jason S. Lueke, Samuel Ariaratnam

Research output: Contribution to journalArticlepeer-review

21 Scopus citations


This paper presents the implementation of an artificial neural network to predict surface heave resulting from shallow subsurface utility installations conducted with horizontal directional drilling. Data gathered from a full factorial field experimentation examining the effects of drilling techniques is utilized in the network development, with the attempt to understand the relationship between construction techniques and resulting surface heave. The developed model is compared to a multivariate linear regression analysis conducted on the raw data, and a sensitivity analysis utilizing the trained network connection weights is conducted to determine which factor has the greatest effect on surface heave development. Further examination of the behavior of the system is provided through a trend analysis which studied the effect of each drilling factor on the predicted surface heave. The results indicate that a neural network would adequately model the relationship between drilling techniques and the resulting surface heave.

Original languageEnglish (US)
Pages (from-to)106-117
Number of pages12
JournalTunnelling and Underground Space Technology
Issue number1
StatePublished - Jan 2006


  • Experimental design
  • Horizontal directional drilling
  • Neural networks
  • Regression analysis
  • Surface heave
  • Trenchless technology

ASJC Scopus subject areas

  • Building and Construction
  • Geotechnical Engineering and Engineering Geology


Dive into the research topics of 'Numerical characterization of surface heave associated with horizontal directional drilling'. Together they form a unique fingerprint.

Cite this