Table 1 Key features of few existing ML-based predictive models for UCS of shales.

Davoodi et al.⁴⁵

Depth, weight on the drill bit (WOB), drill-string rotation speed (RPM), rate of penetration (ROP), and torque (Trq)

Least-squares support-vector machine (LSSVM) and multi-layer extreme learning machine (MELM) algorithms

RMSE = 4.0623,

R² = 0.8975

SD = 5.6835

Absolute average percentage deviation = AAPD = 7.4231

Kolawole and Assaad⁴⁶

Density, treatment period, temperature, Core length, Poisson’s ratio

K-Nearest Neighbor (KNN), Artificial Neural Network (ANN), Decision Tree (DT), and Random Forest (RF)

RF model (UCS:

R² = 0.9613;

MAE = 6.15 MPa; MPE = 2.62%;

VAF = 96.16%;

Mollaei et al.⁴⁷

Shear wave velocity, core properties

MLP, CLM algorithm

R²(MLP) = 0.8727

R²(CLM) = 0.9274

Miah et al.⁴⁸

Resistivity, density, porosity, shear wave velocity

ANN, least square support vector machine, (LS-SVM)

For ANN, RMSE = 2.593

MAPE = 0.21, R2 = 0.9736