-
New prediction model: Air voids
A new prediction model is now available on AsphaltMine for estimating asphalt mixture bulk density and air void content. The model uses an uncertainty-weighted neural network that incorporates laboratory measurement uncertainty into training and evaluation. This allows it to account for differences in the reliability of experimental results rather than treating all measurements equally. The accompanying paper presents the methodology…
-
Visualization tool is live
The AsphaltMine visualization tool is available to any unregistered user. Users can view mean values, uncertainty ranges, and record counts, and can select individual charts to inspect detailed distributions. Upon registration, users gain access to filter data by workspace, mixture type, year, and binder grade, with further options planned for future development. This allows users to focus on specific mixture…
-
First prediction model published
Our new paper presents a physics-based machine learning model for predicting asphalt test results, combining a data-driven approach with physical constraints to improve reliability and interpretability. The main contribution is the methodology itself: a framework that leverages existing experimental data while remaining consistent with known material behavior. Although we demonstrate the approach using the Marshall test, this choice was driven…