RESUMEN
The dynamic analysis of municipal solid waste (MSW) is essential for optimizing landfills and advancing sustainable development goals. Assessing damping ratio (D), a critical dynamic parameter, under laboratory conditions is costly and time-consuming, requiring specialized equipment and expertise. To streamline this process, this research leveraged several novel ensemble machine learning models integrated with the equilibrium optimizer algorithm (EOA) for the predictive analysis of damping characteristics. Data were gathered from 153 cyclic triaxial experiments on MSW, which examined the age, shear strain, weight, frequency, and percentage of plastic content. Analysis of a correlation heatmap indicated a significant dependence of D on shear strain within the collected MSW data. Subsequently, five advanced machine learning methods-adaptive boosting (AdaBoost), gradient boosting regression tree (GBRT), extreme gradient boosting (XGBoost), random forest (RF), and cubist regression-were employed to model D in landfill structures. Among these, the GBRT-EOA model demonstrated superior performance, with a coefficient of determination (R2) of 0.898, root mean square error of 1.659, mean absolute error of 1.194, mean absolute percentage error of 0.095, and an a20-index of 0.891 for the test data. A Shapley additive explanation analysis was conducted to validate these models further, revealing the relative contributions of each studied variable to the predicted D-MSW. This holistic approach not only enhances the understanding of MSW dynamics but also aids in the efficient design and management of landfill systems.
RESUMEN
Bitumen, aggregate, and air void (VA) are the three primary ingredients of asphalt concrete. VA changes over time as a function of four factors: traffic loads and repetitions, environmental regimes, compaction, and asphalt mix composition. Due to the high as-constructed VA content of the material, it is expected that VA will reduce over time, causing rutting during initial traffic periods. Eventually, the material will undergo shear flow when it reaches its densest state with optimum aggregate interlock or refusal VA content. Therefore, to ensure the quality of construction, VA in asphalt mixture need to be modeled throughout the service life. This study aims to implement a hybrid evolutionary polynomial regression (EPR) combined with a teaching-learning based optimization (TLBO) algorithm and multi-gene genetic programming (MGGP) to predict the VA percentage of asphalt mixture during the service life. For this purpose, 324 data records of VA were collected from the literature. The variables selected as inputs were original as-constructed VA, VA orig (%); mean annual air temperature, MAAT (°F); original viscosity at 77 °F, η o r i g , 77 (Mega-Poises); and time (months). EPR-TLBO was found to be superior to MGGP and existing empirical models due to the interquartile ranges of absolute error boxes equal to 0.67%. EPR-TLBO had an R2 value of more than 0.90 in both the training and testing phases, and only less than 20% of the records were predicted utilizing this model with more than 20% deviation from the observed values. As determined by the sensitivity analysis, η o r i g , 77 is the most significant of the four input variables, while time is the least one. A parametric study showed that regardless of MAAT , η o r i g , 77 , of 0.3 Mega-Poises, and VA orig above 6% can be ideal for improving the pavement service life. It was also witnessed that with an increase of MAAT from 37 to 75 °F, the serviceability of asphalt concrete takes 15 months less on average.
