Cho, Sung Eun (2025) Machine learning approaches for improving construction materials and pavement systems. PhD thesis, Virginia Polytechnic Institute and State University, USA.
Abstract
The construction industry is faced with unprecedented challenges of population growth, urbanisation, and worldwide climatic change. These necessitate the development of optimised construction and pavement materials that are cost-effective, sustainable, resilient, and long-lasting. The conventional experimental design approaches to designing construction materials and assessing pavement performance are time-consuming, expensive, and unable to investigate the complex interactions of the different factors influencing their performance. Therefore, this dissertation applies machine learning (ML) techniques to predictive modelling and optimisation, forming a data-driven strategy for material selection and performance prediction. The dissertation is focused on four primary studies. The first uses ML algorithms including Categorical Boosting (CatBoost) to predict the unconfined compressive strength of cement-treated soil for deep mixing, demonstrating that ML models can enhance the accuracy of forecasts significantly relative to nonlinear regression. The second examines how crumb rubber particle size affects the strength of rubberised concrete, using the Synthetic Minority Over-sampling Technique (SMOTE) and CatBoost to build a predictive model, finding that crumb rubber content has greater impact on predicted strength than particle size. The third employs ML to predict the compressive strength of concrete with steel furnace slag (SFS) aggregates - including basic oxygen furnace (BOF), electric arc furnace (EAF), and ladle metallurgy furnace (LMF) slag types - using a SMOTE and Light Gradient Boosting Machine (LightGBM) K-fold model, finding that the amount of SFS aggregate was more dominant in prediction than SFS type. The fourth employs supervised and unsupervised ML models to predict the International Roughness Index (IRI) of concrete pavements from the Long-Term Pavement Performance (LTPP) database, concluding that material properties, traffic load, and climate conditions were crucial to IRI prediction and that hierarchical clustering models suggest pavement performance could be regionally divided for design purposes. This dissertation improves prediction, decreases dependence on expensive experimental tests, and supports the construction of sustainable infrastructure.
| Item Type: | Thesis (Doctoral) |
|---|---|
| Thesis advisor: | Brand, Alexander S |
| Index terms: | construction material, sampling, minority, clustering, dissertation, construction industry, interaction, urbanization, aggregate, experimental design, performance prediction, particle size, database, population, furnace, slag, machine learning, material property, predictive modelling, strategy, compressive strength, accuracy |
| Subjects: | urban planning, waste management, materials science, research dissemination and communication, behavioral psychology, demography, material analysis and testing, data science, artificial intelligence, prediction and forecasting, building materials, data collection methods, research design and methodology, mechanical systems, industry analysis, data management, sociology, material properties and characteristics, professional development, management, performance management |
| Topics: | Engineering Principles, Sustainability, Quality Management, Ethics, Information Management, Construction Materials, Research Practice, Business Strategy, Governance, Urban Studies, Digital Applications |
| Descriptive scope: | 5 PCTEA |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here