Show simple item record

dc.contributor.authorChen, Chunjiang
dc.contributor.supervisorPeng Wuen_US
dc.contributor.supervisorYongze Songen_US
dc.date.accessioned2025-05-09T00:33:04Z
dc.date.available2025-05-09T00:33:04Z
dc.date.issued2025en_US
dc.identifier.urihttp://hdl.handle.net/20.500.11937/97702
dc.description.abstract

This study introduces a geocomplexity-enhanced machine learning (GML) model that integrates spatial methodologies to uncover influencing factors of crack severity obtained from human inspection and laser scanning. These two aspects, representing existing surface crack condition, are then integrated with a risk of deterioration to develop a comprehensive crack evaluation framework.

en_US
dc.publisherCurtin Universityen_US
dc.titleLarge-scale Pavement Crack Evaluation and Prediction using a Novel Spatial Machine Learning Approachen_US
dc.typeThesisen_US
dcterms.educationLevelPhDen_US
curtin.departmentSchool of Design and the Built Environmenten_US
curtin.accessStatusFulltext not availableen_US
curtin.facultyHumanitiesen_US
curtin.contributor.orcidChen, Chunjiang [0000-0002-9244-2257]en_US
dc.date.embargoEnd2027-04-29


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record