International Roughness Index (IRI) is a pavement performance indicator which reflects not only the pavement condition but also the ride quality and comfort level of road users. The aim of this paper is to develop an accurate IRI prediction model for flexible pavements using both multiple linear regression analysis and artificial neural networks (ANNs). The models were developed based on the Long-Term Pavement Performance Database. The data were collected for both original and overlaid flexible pavements from the general pavement studies (GPS-1, GPS-2 and GPS-6) and the specific pavement studies (SPS-1, SPS-3 and SPS-5). The final database consisted of 506 sections with 2439 observations. The proposed models (regression and ANNs) predict IRI as a function of pavement age, initial IRI (IRI just after pavement construction), transverse cracks, alligator cracks and standard deviation of the rut depth. The regression model yielded a coefficient of determination (R²) value of 0.57 while the ANNs model resulted in a much higher R² value of 0.75.

International Roughness Index (IRI) is a key parameter in pavement performance evaluation. This study investigates developing a reliable prediction model that can be used to estimate IRI of rigid pavements using innovative machine learning techniques. Optimally Pruned Extreme Learning Machine (OP-ELM) and Wavelet analysis are integrated to improve the OP-ELM results and design a novel hybrid Wavelet-OPELM (WOPELM) model for the IRI prediction. The proposed model is compared statistically to the OP-ELM and conventional feed-forward Artificial Neural Network (ANN) as well as regression model with respect to their efficiency to predict IRI of jointed plain concrete pavement (JPCP) sections in USA. The relevant data was collected from the Long-Term Pavement Performance (LTPP) database. Eight input variables, initial IRI, pavement age, transverse cracks, percent joints spalled, flexible and rigid patching areas, total joint faulting, freeze index, and percent subgrade passing No. 200 U.S. sieve, are assessed and used to predict the IRI. The results show that the initial IRI, total joint faulting, and freezing index are the most significant parameters for IRI prediction. The WOPELM is found to be a robust and more accurate modelling technique compared to OP-ELM, ANN, and regression for IRI prediction with only a 7% prediction error.

The hot-mix asphalt (HMA) dynamic modulus ($E^{*}$ ) is a fundamental mechanistic property that defines the strain response of asphalt concrete mixtures as a function of loading rate and temperature. It is one of the HMA primary material inputs for common software for the mechanistic-empirical design of pavements. Laboratory testing of dynamic modulus requires expensive advanced testing equipment that is not readily available in the majority of laboratories in Middle Eastern countries, yet some of these countries are looking for implementing new pavement design methods such as those given in current standards. Thus, many research studies have been dedicated to develop predictive models for $E^{*}$ . This paper aims to apply artificial neural networks (ANNs) for $E^{*}$ predictions based on the inputs of the models most widely used today, namely: Witczak NCHRP 1-37A, Witczak NCHRP 1-40D and Hirsch $E^{*}$ predictive models. A total of 25 mixes from the Kingdom of Saudi Arabia (KSA), and 25 mixes from Idaho state were combined together in one database containing $\mathrm{3,720}{E}^{*}$ measurements. The database also contains the volumetric properties and aggregate gradations for all mixes as well as the binder complex shear modulus ($G_b^{*}$ ), phase angle ($\delta$ ), and Brookfield viscosity ($\eta$ ). A global sensitivity analysis (GSA) was applied to investigate the most significant parameters that affect $E^{*}$ predictions. The GSA procedures based on the Fourier amplitude sensitivity test (FAST) and Sobol sequence approaches were implemented in commercially available software to evaluate the sensitivity of the three regression models to their input parameters. The ANN models, using the same input variables of the three predictive models, generally yielded more accurate $E^{*}$ predictions. Moreover, the GSA showed that aggregate, binder, and mixture representative parameters have convergent effects on $E^{*}$ predictions using one model applied, whereas binder representative parameters have the dominant effect on $E^{*}$ predictions using both of the other two models.

This paper represents the results of a comprehensive experimental work on developing high performance concrete mixes containing different percentages of electric arc furnace steel slag (EAFSS) coarse aggregate (0, 25, 50, 75, and 100% by weight) for sustainable pavements. The use of steel slag powder (SSP) and silica fume (SF) as a mineral filler was also investigated. Mechanical properties of concrete such as compressive, splitting tensile and flexural strengths, modulus of elasticity, permeability, and thermal conductivity, were measured in the laboratory. The morphological and microstructural properties of the investigated steel slag were also determined. Finally, the field performance of the investigated concrete mixes was predicted using the AASHTOWare Pavement ME for a typical Jointed Plain Concrete Pavement (JPCP) system in terms of transverse cracking, faulting, and roughness. The results of this research indicate that, all investigated mechanical properties for steel slag mixes are better than the natural aggregate mix with optimum mechanical properties and performance for the concrete mix with 50% EAFSS. Using the SSP powder with or instead of SF did not show significant improvement in mechanical properties/performance. The results emphasise that EAFSS is a viable sustainable construction material for rigid pavements.

Nternational Roughness Index (IRI) is an important parameter that indicates the ride quality and pavement condition. In this study, an Artificial Neural Network (ANN) model was developed to predict the IRI for Jointed Plain Concrete Pavement (JPCP) sections. The inputs for this model are: initial IRI value, pavement age, transverse cracking, percent joints spalled, flexible and rigid patching areas, total joint faulting, freezing index, and percent subgrade passing No. 200 U.S. sieve. This data was obtained from the Long Term Pavement Performance (LTPP) Program. It is the same data and inputs used for the development of the Mechanistic-Empirical pavement Design Guide (MEPDG) IRI model for JPCP. The data includes a total of 184 IRI measurements. The results of this study shows that using the same input variables, the ANN model yielded a higher prediction accuracy (coeficint of determination: R²= 0.828, and ratio of standard error of estimate (predicted) to standard deviation of the measured IRI values: S_e/S_y=0.414) compared to the MEPDG model (R²= 0.584, S_e/S_y=0.643). In addition, the bias in the predicted IRI values using the ANN model was significantly lower compared to the MEPDG regression model.