One of the most important components of pavement management systems is predicting the deterioration of the network through performance models. The accuracy of the prediction model is important for prioritizing maintenance action. This paper describes how the accuracy of prediction models can have an effect on the decision-making process in terms of the cost of maintenance and rehabilitation activities. The process is simulating the propagation of the error between the actual and predicted values of pavement performance indicators. Different rate of error (10%, 30%, 50%, 70%, and 90%) was added into the result of prediction models. The results showed a strong correlation between the prediction models’ accuracy and the cost of maintenance and rehabilitation activities. The cost of treatment (in millions of dollars) over 20 years for five different scenarios increased from ($54.07–$92.95), ($53.89–$155.48), and ($74.41–$107.77) for asphalt, composite, and concrete pavement types, respectively. Increasing the rate of error also contributed to the prediction model, resulting in a higher benefit reduction rate.

This paper describes the process and outcome of deterioration modeling for three different pavement types (asphalt, concrete, and composite) in the state of Iowa. Pavement condition data is collected by the Iowa Department of Transportation (DOT) and stored in a Pavement-Management Information System (PMIS). In the state of Iowa, the overall pavement condition is quantified using the Pavement Condition Index (PCI), which is a weighted average of indices representing different types of distress, roughness, and deflection. Deterioration models of PCI as a function of time were developed for the different pavement types using two modeling approaches. The first approach is the long/short-term memory (LSTM), a subset of a recurrent neural network. The second approach, used by the Iowa DOT, is developing individual regression models for each section of the different pavement types. A comparison is made between the two approaches to assess the accuracy of each model. The results show that the LSTM model achieved a higher prediction accuracy over time for all different pavement types.

Safety performance is a crucial component of highway network performance evaluation. Besides their devastating impact on roadway users, traffic crashes lead to substantial economic losses on both personal and societal levels. Due to the complexity of crash events and the unique conditions in each country and state, empirical local calibration for the correlation between attributes of interest and the safety performance is always recommended. Limited studies have established a procedure to analyze the impact of pavement condition on traffic safety in a risk analysis scheme. This study presents a thorough analysis of some roadway departure crashes which occurred in Iowa between 2006 and 2016. All crash records were mapped onto one-mile segments with known traffic volume (i.e., AADT), posted speed limits (SL), skid numbers (SN), ride qualities (IRI), and rut depths (RD) in a geographic information system (GIS) database. The crash records were correlated to the pavement surface condition (i.e., SN, IRI, and RD) using negative binomial regression models. Moreover, a novel risk analysis framework is introduced to perform crash risk assessment and evaluate the possible consequences for a given combination of events. The analysis shows a significant impact of pavement skid resistance on roadway-departure crashes under all accident conditions and severities. Risk analysis will facilitate coordination between the pavement management system and safety management system in the future, which will help with optimizing the overall highway network performance.

This paper investigates the effects of segment length, line types, and imputed retroreflectivity values on pavement-marking retroreflectivity and crash frequency analyses. Road data, crash data, pavement condition data, and pavement-marking retroreflectivity data from Iowa Department of Transportation (DOT) databases were acquired and spatially integrated. Data sets for 1-, 3-, and 5-mi segments were prepared to investigate the effect of segmentation. Additional data sets with imputed and measured retroreflectivity data were prepared for comparison. A series of negative binomial regression analyses were run to estimate the expected number of crashes on varying segment lengths and data subsets based on the two retroreflectivity collection methods. The findings show that using smaller segments and data sets with measured retroreflectivity rather than imputed retroreflectivity leads to a more significant relationship between the retroreflectivity of longitudinal pavement markings and crash frequency....

State highway agencies have been collecting a massive amount of pavement condition data by using automated collection technologies. This rich historical data set has great potential to support data-driven pavement management decisions such as the selection and timing of pavement maintenance options. However, most agencies face various technical and data integration issues that result in serious underutilization of the collected data. Unless those barriers are clearly identified, communicated and resolved, it will significantly reduce the efficiency and effectiveness of the financial investments made to collect the pavement condition data and meet the Federal Highway Administration’s direction of performance-based project delivery and asset management through the Moving Ahead for Progress in the 21st Century (MAP-21) and Fixing America’s Surface Transportation (FAST) Acts. This study identifies technical challenges and data integration barriers that prevent the effective use of historical data when an agency tries to implement a data-driven process to evaluate the performance of pavement treatments. The study uses the historical data collected from one state department of transportation as a representative highway agency. A set of recommendations is presented to help state highway agencies to fully take advantage of the pavement condition data collection efforts for implementing pavement asset management.

Effective pavement management systems are essential for accurately predicting pavement conditions and efficiently planning and scheduling maintenance, rehabilitation, and reconstruction activities. Significant efforts are dedicated to developing accurate pavement condition prediction models using machine learning (ML) at the state level. Conversely, insufficient investment, poor quality, and large variations in local roads data have resulted in less attention to modeling local pavement conditions. This study develops eight Bayesian-optimized single-estimator and ensemble ML classification models to predict local pavement roughness. Moreover, the classification granularity of pavement condition was investigated to assess its impact on the predictive power of various ML models. The results reveal that ML classification models with fewer classes exhibit higher accuracy and more stability in precision over recall values, in contrast to models with larger number of classes. The ensemble ML models surpass their single-estimator counterparts, with the category boosting algorithm demonstrating the highest performance, achieving testing accuracies of 0.77 and 0.65 for the three-level and five-level classifications, respectively. Hence, it is recommended to employ ensemble ML algorithms and a smaller number of classes to develop reliable, accurate, and stable predictive models for local roads with imbalanced condition data. This research helps transportation agencies improve their pavement condition prediction, thereby optimizing pavement management and resource allocation.