In the original publication [...].
Reliable knowledge of temperature distribution within asphalt pavements, both over time and across depth, is essential for pavement diagnostics and maintenance planning due to the strong temperature dependence of asphalt mechanical behavior. Inadequate temperature correction may bias network-level indicators derived from FWD and TSD measurements, while accurate surface-temperature prediction is also important for winter maintenance.This paper presents a case study and feasibility analysis of machine-learning-based prediction of asphalt-layer temperature using one year of continuous field data from an instrumented pavement section. Two modeling approaches are evaluated: recurrent neural networks (RNN) for time-series analysis and gradient-boosted decision trees (XGBoost) for tabular data with temporal encoding.The results show that RNN models accurately reproduce diurnal and seasonal temperature variations, whereas XGBoost models provide comparable accuracy with substantially lower computational cost. A depth-aware XGBoost formulation enables accurate interpolation of temperature across pavement depth, achieving a mean error of approximately 1 °C (R² ≈ 0.99).The findings confirm the practical potential of data-driven temperature prediction and support the use of efficient tree-based models for temperature correction and integration into pavement-management and winter-maintenance systems.
Attenuated Total Reflection Fourier Transform Infrared spectroscopy has become a popular spectroscopic technique in bituminous binder analysis. However, comparable results are not obtainable yet due to differences in devices, measurement routines, sample preparation procedures, and spectral evaluation. Thus, the Task Group 1 of the RILEM TC 295-FBB: “Fingerprinting bituminous binders using physicochemical analysis” focuses on bringing this method towards pre-standardization. This study evaluates the reproducibility and consistency from round robin test, where 21 participating laboratories performed six different preparation techniques on three different binders in an unaged, short-term, and long-term aged state. A total of 6461 spectra were recorded and evaluated for their mean, standard deviation and coefficient of variation (CV) in the spectral region between 1800 and 600 cm−1. The results show that the solid sample preparation methods provide excellent reproducibility, with a coefficient of variation below 2
The FWD is commonly used to conduct a non-destructive evaluation of the capacity of the pavement. The layered pavement is loaded locally by falling weight, and deflection is recorded at many points. Based on these results, if the pavement geometry is known, the mechanical properties of the pavement may be determined using the back-calculation approach. Analytical, numerical, or ML methods can be used for back-calculation. An analytical solution for a multi-layered structure leads to non-linear relationships for the thickness or stiffness of each layer, but provides an accurate solution. The other methods, like numerical or ML methods, are just approximation methods with different levels of accuracy. In this paper, the accuracy of the XGBoost ML regression model in predicting mechanical and geometrical pavement parameters was estimated. The database was generated from a static analytical solution of an axially symmetrical problem implemented in the form of JPav software and then explored by training regression models to predict the moduli and thickness of pavement layers. Two other databases were created using PCA (Principal Component Analysis) and FDM-like (Feature Difference Method) to compare models trained with the complete deflection database. The results showed that models trained with the complete deflection database had the best average prediction performance compared to the other two. In contrast, models trained with the database pre-processed by PCA showed a similar predicting performance to that of the previous models, but with a slight loss in precision. Models trained with the database pre-processed by the FDM-like approach exhibited excellent prediction on some features but performed worse on the rest. The primary objective of this work is to develop a model that enables the determination of pavement layer thickness and moduli from the deflections obtained in FWD tests. The analysis carried out allowed us to conclude that it is possible to obtain some pavement variables from the deflections, while others require a more sophisticated approach.
Ograniczenie hałasu drogowego przez stosowaniecichych nawierzchni jest jednym z wyzwań stojących przedwykonawcami wierzchnich warstw dróg. Dobór odpowiedniegokruszywa może temu problemowi zaradzić. W artykule przedstawionowyniki badań hałaśliwości nawierzchni w odniesieniudo jej właściwości przeciwpoślizgowych. Na podstawie uzyskanychwyników wskazano cechy kruszywa, które pozwolą obniżyćhałaśliwość nawierzchni przy zachowaniu odpowiedniegopoziomu bezpieczeństwa użytkowników drogi
