A realistic prediction of excess pore water pressure generation and the onset of liquefaction during earthquakes are crucial when performing effective seismic site response analysis. In the present research, the validation of two pore water pressure (PWP) models, namely energy-based GMP and strain-based VD models implemented in a one-dimensional site response analysis code, was conducted by comparing numerical predictions with highquality seismic centrifuge test measurements. A careful discussion on the selection of input soil parameters for numerical simulations was made with particular emphasis on the PWP model parameter calibration which was based on undrained stress-controlled/strain-controlled cyclic simple shear (CSS) tests carried out on the same sand used in the centrifuge test. The results of the study reveal that the energy-based model predicts at all depths peak pore water pressures and dissipation behaviour in a satisfactory way with respect to experimental measurements, whereas the strain-based model underestimates the PWP measurements at low depths. Further comparisons of the acceleration response spectra illustrate that both the strain- and energy-based models provide higher computed spectral accelerations near the ground surface compared with the recorded ones, whereas the agreement is reasonable at middle depth.

In this study, a novel data-driven approach is carried out to predict the pore pressure generation of liquefiable clean sands during cyclic loading. An extensive and comprehensive database of actual stress-controlled cyclic simple shear test results in terms of pore pressure time histories is gathered from a large number of experiments. While the classical machine learning (ML) algorithms help predict the number of liquefaction cycles in a few models, the desired level of accuracy in predicting the actual trend and robustness in pore pressure build-up is only achieved in deep learning (DL) methods. Results indicate that the Long-Short Term Memory (LSTM) working model, employed with Stacked LSTM and the Windowing data processing method, is necessary for making fairly good cyclic pore pressure build-up predictions. This study proposes a model that can ultimately be utilised to predict the pore pressure response of in-situ liquefiable sandy soil layers without resorting to plasticity-based complex theoretical models, which has been the current practice. The robustness achieved in the model reassures the reliability of the study, raising confidence in developing data-driven constitutive models for soils that have the potential to replace conventional plasticity-based theories.