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 and demonstrates its application to asphalt volumetric properties, with potential for use in other materials tests where measurement uncertainty is known.
Read the paper and try the new bulk density and air voids prediction model on AsphaltMine.
