Synthetic Subgrade Dataset for Structural Number Prediction of Flexible Pavements

This dataset contains 10,000 synthetic records of subgrade soil properties and their corresponding Structural Numbers (SN) for flexible pavement design. The dataset was generated using the empirical equation of Mohammad et al. (1999) to compute the resilient modulus (Mr) from basic soil index properties, followed by the AASHTO 93 design equation solved via the bisection method to obtain SN. Input variables include moisture content (w%), dry unit weight (γd), and plasticity index (PI), covering subgrade soils classified as A-4, A-6, and A-7-6 (AASHTO). Fixed AASHTO 93 design parameters: W18=5×10⁶ ESALs, ZR=−1.282, So=0.45, ΔPSI=2.5. This dataset was used to train and evaluate machine learning models for SN prediction as part of a research article submitted to TICEC 2026.