SPR-4714: Use of Machine Learning Methods to Obtain a Reliable Predictive Model for Resilient Modulus of Subgrade Soil

Project Details
STATE

IN

SOURCE

RIP

START DATE

10/01/22

END DATE

03/31/24

RESEARCHERS

Sara Khoshnevisan, Medhi Norouzi

SPONSORS

Purdue University, Indiana Department of Transportation JHRP

KEYWORDS

machine learning, Modulus of resilience, Soils, Subgrade (Pavements)

Project description

This research will use machine learning to develop/train data model(s) for predicting the resilient modulus of soil in the state of Indiana. The developed model(s) will reduce the need for routine iterative laboratory testing conducted for obtaining the resilient modulus of soil, which is complicated, resource intensive, time consuming, and expensive. In addition, based on the developed model(s), recommendations will be provided for future sampling locations.
TOP