A Machine Learning Tool for Pavement Design and Analysis

Guangwei Yang, Kamyar C. Mahboub, Ryan L. Renfro, Clark Graves, Kelvin C.P. Wang

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


The AASHTOWare Pavement ME Design program is a pavement analysis tool, which is typically used for design purposes through an iterative trial-and-error process. To help the designer with a reasonable starting point in this iterative process, this paper introduces a machine learning method to embrace the recently updated models in AASHTOWare Pavement ME Design software for pavement design. A total number of 79,600 pavement design scenarios (55,800 for flexible pavements and 23,800 for rigid pavements) were performed using the AASHTOWare Pavement ME Design software to consider various design inputs, such as: design life, traffic volume, climate zone, thickness, and modulus of pavement layers. The inputs and outputs of these design scenarios were used to develop the multioutput Random Forests model to simultaneously predict multiple pavement distresses and thicknesses of pavement layers. The results indicate that the multi-output Random Forests model can accurately predict pavement distresses and thicknesses for asphalt and concrete pavements. This tool will simplify pavement design procedure based on the models in the AASHTOWare Pavement ME Design software.

Original languageEnglish
Pages (from-to)207-217
Number of pages11
JournalKSCE Journal of Civil Engineering
Issue number1
StatePublished - Jan 2023

Bibliographical note

Publisher Copyright:
© 2022, Korean Society of Civil Engineers.


  • AASHTOWare pavement ME design
  • Machine learning
  • Multi target regression
  • Multi-output random forests
  • Pavement performance
  • Pavement thickness design

ASJC Scopus subject areas

  • Civil and Structural Engineering


Dive into the research topics of 'A Machine Learning Tool for Pavement Design and Analysis'. Together they form a unique fingerprint.

Cite this