Table 3 Prediction performance metrics of the Random Forest surrogate model for all 200 RC wall specimens. The table reports the coefficient of determination (\(R^2\)), mean absolute error (MAE), root mean squared error (RMSE), and 95% confidence intervals for initial stiffness \(K_{0}\), yield displacement \(\delta _{y}\), and post-yield hardening ratio \(\alpha\).

From: Digital twin-based machine learning framework for predicting nonlinear seismic response of reinforced concrete shear walls using analytical data