Table 1 The data variables.

From: Enhanced probabilistic prediction of pavement deterioration using Bayesian neural networks and cuckoo search optimization

Variables

Description

Variable type

Structure and material data

 Thickness of surface layers

Sum of thickness of upper, middle, and lower surface layers in Fig. 1

Numerical

 Materials of base courses

Mixtures of cement, lime, industrial waste, or asphalt with soil or gravel

Categorical

Traffic volume data

 AADTT

Average annual daily truck traffic

Numerical

 AADT

Average annual daily traffic

Numerical

Climate and environmental data

 Total high temperature days

Total number of days with daily average temperature > 25 ℃ in a year

Numerical

 Number of consecutive high temperature

Number of consecutive 3 days or more with daily average temperature > 25 ℃ in a year

Numerical

 Total low temperature days

Total number of days with daily average temperature < 0 ℃ in a year

Numerical

 Number of consecutive low temperature

Number of consecutive 3 days or more with daily average temperature < 0 ℃ in a year

Numerical

Pavement condition data

 PCI of previous year

PCI: Pavement surface condition index, with values ranging from 0 to 100, where 0 indicates the worst pavement condition and 100 indicates the best pavement condition

Numerical

 PCI of current year

Numerical

Other data

 Road age

Current year—year of road completion

Numerical