Cracking characterization is one of the most important tasks in automated pavement data analysis. Although cracking detection and segmentation algorithms have become more reliable in recent years, accurate cracking classification remains a constant challenge to pavement engineers. Conventionally, manual recognition uses cracking orientation and topological features to classify cracking into different types such as alligator cracking and transverse cracking. However, the rules to classify cracking are often complicated and subjective, which compromises the reliability of computerized implementation. This study develops a support vector machine (SVM)–based method to intelligently identify cracking types in an automated manner. Pavement cracks are grouped using a minimum rectangular cover (MRC) model. Using the relative location, orientation, and size of the MRC, as well as the cracking characteristics such as cracking density and cracking connectivity, three SVM models are compared in this study. It is found that an 88.07% accuracy is achieved for 10,134 MRCs collected from four highway sections using the two-phase SVM model. The proposed methodological framework would improve overall accuracy in cracking classification.

Because of potential differences between national and local conditions, the Mechanistic–Empirical Pavement Design Guide (MEPDG) should be calibrated to a local level. Arkansas has invested heavily in efforts to implement the MEPDG. This paper summarizes the initial local calibration of flexible pavement models in the MEPDG for Arkansas. Data from the Long-Term Pavement Performance (LTPP) database and local pavement management system (PMS) were used. The solver function in Microsoft Excel was used to optimize the coefficients for alligator cracking. Iterative runs of the MEPDG by means of discrete calibration coefficients were conducted to optimize rutting models. In general, the alligator cracking and rutting models are improved by calibration. However, a question remains about the suitability of the calibrated models for routine design. Many default values were used in the MEPDG because of a lack of data. It is recommended that additional sites be established and a more robust data collection procedure be implemented for future calibration efforts. The difference in the definitions of transverse cracking between the MEPDG and the LTPP may be critical to data collection and identification. Thermal cracking should be specifically identified in a transverse cracking survey to calibrate the transverse cracking model in MEPDG. The procedure using LTPP and PMS data for local calibration of the MEPDG in Arkansas is established. Additional development of database software for data manipulation, preprocessing, and quality control—under way in Arkansas—will significantly streamline the calibration process.

A key to the use of weigh-in-motion (WIM) traffic data for the Mechanistic-Empirical Pavement Design Guide (MEPDG) is to be able to successfully recognize the differences in loading patterns and to estimate the full axle-load spectrum data occurring under different conditions. However, how to identify these patterns on the basis of the large amount of WIM data remains a challenge. In this paper, WIM data collected in the state of Arkansas are analyzed by using cluster analysis methodologies to identify groups of WIM sites with similar traffic characteristics on the basis of the MEPDG-required traffic attributes. Case studies are presented and the cluster results are discussed. Combining the loading clusters, four long-term transportation planning factors currently adopted in Arkansas, including the modified Arkansas primary highway network (APHN) classification, demography, geography, and region attribute (rural or urban) of a highway under design, are adopted as the influencing criteria to develop the truck loading groups. The most significant influencing criteria are identified by using Fisher’s exact test. Consequently, truck loading groups and their categorical logit models are developed in the paper. The developed method for determining truck loading groups will simplify the understanding and applicability of the traffic patterns and ultimately ease the preparation of the traffic load spectra inputs on the basis of WIM data for the MEPDG procedure.

“Reliability,” as defined in the Mechanistic–Empirical Pavement Design Guide (MEPDG), is an aggregated indicator defined as the probability that each of the key performance measures will be less than a selected critical level over the design period. Being such a complex system, the MEPDG—which is not a single closed-form design equation—cannot depend on classic reliability methods. Monte Carlo simulation is suitable for a robust reliability analysis but is impractical because of the extensive computation time required for any reasonable analysis with the MEPDG. The development of surrogate models for performance predictions becomes an option to represent the comprehensive modeling capability of the MEPDG efficiently. Improvements to the MEPDG reliability model based on several statistical methods are described. Five tasks are detailed. First, the MEPDG is calibrated to local conditions to reduce potential bias and variation from the national calibration. Then, risk analysis and screen analysis are conducted to determine the significant variables to include in surrogate models. Next, a comprehensive experimental design effectively plans MEPDG simulations. Then, response surface models of MEPDG are built through regression analysis. Finally, probabilistic design is achieved by Monte Carlo simulation. The result of these efforts is a state-specific MEPDG-based probabilistic pavement design tool kit named ReliME. This framework provides engineers more flexibility in data acquisition, design alternatives, optimization, and quality control. The framework's successful application in Arkansas could easily be used in other states and incorporated into future mechanistic–empirical pavement design software.

State highway agencies need pavement-condition data to select candidates for pavement maintenance and rehabilitation. However, it is a challenge for pavement engineers to simultaneously assess a number of attributes that represent different aspects of pavement condition. In conventional practice, empirical comprehensive evaluation methodologies, such as fuzzy set theory and analytical hierarchy process, have been used to aggregate multiple distresses into integrated pavement-performance indices. These methodologies, however, are mostly based on experts’ or engineers’ judgment rather than data-driven approaches. In this paper, a framework of applying a data-driven approach to conduct comprehensive pavement evaluation and ranking is presented. The method of Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) is introduced and applied to rank pavement sections with various evaluation attributes. Principal component analysis (PCA) is employed to combine distresses with high correla...