Graduation Semester and Year




Document Type


Degree Name

Doctor of Philosophy in Civil Engineering


Civil Engineering

First Advisor

Ali Abolmaali


In this dissertation, through utilizing various artificial intelligence-based as well as statistical models, an effort has been made to investigate the deterioration of sewer pipes. Once the deterioration rates of sewer pipes are estimated, by assuming failure criteria, as specified in the dissertation, the associated service lives for the sewer pipes can therefore be estimated. However, it should be noted that for different sewer pipes and based upon the availability of suitable data, and due to various failure modes that could transpire in various sewer pipes, the results will thus be subjected to uncertainties and variations. In other words, depending on different sewer pipes, the adequacy and the availability of suitable data, the decision-makers’ priorities and failure criteria, the estimated service lives as well as the associated deterioration curves could be subjected to variation. Selecting a suitable model plays an important role in reducing the amount of uncertainty associated with estimation of service life of sewer pipes. In order to estimate the service lives of sewer pipes, the first step is to estimate the rate of deterioration which affects the condition rating of sewer pipes. Next, by designating a certain threshold or cut-off value, the service life of sewer pipes could thus be estimated as well. Therefore, depending on the type of selected deterioration modeling, the assignment of threshold (cut-off value) needs to be conducted with adequate engineering judgement. Additionally, based upon the criteria of decision-makers, the certain threshold for service life may be subject to further change and improvement. Hence, the suitable modeling approach may differ for various projects and sewer pipes; i.e. a model which yields suitable results for one project may not necessarily yield suitable and reliable results in another project. This stems from the assumptions and uncertainties associated with each of the modeling approaches.


Artificial intelligence, Statistical modeling, LightGBM, CatBoost


Civil and Environmental Engineering | Civil Engineering | Engineering


Degree granted by The University of Texas at Arlington