The utilization of waste polyethylene terephthalate (WPET) as aggregate substitutes in pavement has been extensively promoted because of its environmental advantages. However, previous studies have shown that a high percentage of WPET reduces the performance of the pavement. To increase the durability of pavement and mitigate the environmental issues caused by WPET, WPET is treated with gamma-irradiation as a component in asphalt mixtures. The study objectives were to investigate the feasibility of using WPET granules as a sustainable aggregate on asphalt mixture stiffness and rutting and predict the asphalt mixture performance containing irradiated WPET via an RSM-ANN-framework. To achieve the objectives, stiffness and rutting tests were conducted to evaluate the WPET modified mixtures’ performance. The result indicated that samples containing 40% irradiated WPET provided a better performance compared to mixtures containing 20% non-irradiated WPET, increasing the stiffness by 27% and 21% at 25 °C and 40 °C, respectively, and rutting resistance by 11% at 45 °C. Furthermore, both predictive models developed demonstrated excellent reliability. The ANN exhibited superior performance than the RSM. The utilization of WPET as aggregate in asphalt mixtures represents a way to addressing related recycling issues while also improving performance. With gamma-irradiation treatment, the utilization of WPET can be increased with improved asphalt mixture performance.

Machine learning (ML) models are excellent alternative solutions to model complex engineering issues with high reliability and accuracy. This paper presents two extensively explored ensemble models for predicting asphalt pavement temperature, the Markov chain Monte Carlo (MCMC) and random forest (RF). The RF and multiple MCMC (RF-MCMC) were used to hybridise the proposed algorithms for the optimal prediction of asphalt pavement temperature. This study used thermal instruments to measure the asphalt pavement temperature in Gaza Strip, Palestine. The temperature measurements were made at a two-hour interval from March 2012 to February 2013. The temperature data was used to model the pavement temperature. More than 7200 measured pavement temperatures were used to train and validate the proposed models. The validation showed that the ML models are satisfactory. The modelling results ensured the value of the proposed hybridisation models in predicting the asphalt pavement temperature levels. The developed hybrid algorithms regression model achieved acceptable and better prediction results with a coefficient of determination (R2) of 0.96. Generally, the results confirmed the significance of the proposed hybrid model as a reliable alternative computer-aided model for predicting asphalt pavement temperature.

The application of statistical modeling and optimization approaches such as response surface methodology (RSM) is important for the excellent potential to tackle different constraints and goals and the analysis of the relationships between independent factors influencing a particular response. This chapter provides a simple yet detailed literature review on the utilization of RSM for the design of experiments, modeling, and optimization of virgin and alternative materials into asphalt binder and mixtures for sustainability. Meanwhile, an in-depth analysis based on the literature reviewed in terms of asphalt binder modification employing RSM with various independent parameters were summarized. Also, a critical review of the application of RSM to optimize the engineering and mechanical performance characteristics of asphalt concrete mixtures is presented in this chapter. The current chapter concluded that the use of RSM statistical analysis in a highway materials perspective provides a broader understanding of the factors that control pavement performance throughout the pavement service life.