Creep parameter inversion and long-term deformation prediction of a near-dam slope considering spatio-temporal deformation data during construction and impoundment period

Adequate calibration of material parameters is the prerequisite for credible long-term deformation prediction of reservoir bank slopes. In this study, a creep parameter inversion method accounting for water effect and mechanical characteristics of rock masses is proposed. The elasto-viscoplastic model based on internal variables is introduced in inversion, which incorporates transient pore pressure effect, progressive strength degradation in hydro-fluctuation belt and saturated zone, as well as dam-foundation interaction induced by periodic water level fluctuations. The inversion process integrates a metaheuristic algorithm (improved adaptive genetic algorithm, IAGA) with a BP neural network-based (BPNN) surrogate model. A segmented and incremental strategy is implemented in objective function to capture the spatio-temporal heterogeneity of the deformations observed at each point. Besides, random perturbation coefficients, derived from statistical experimental results of multiple hydropower projects, are introduced to constrain friction coefficient (f) and cohesion (c), addressing the heteroscedastic nature of strength parameters. Leveraging deformation measurements spanning approximately 17 years from 27 observation points during the construction and impoundment periods, an inversion is performed on 48 creep parameters across 8 materials of a near-dam slope. Based on the calibrated parameters, predictions are made for the convergence time, stabilization time, and ultimate deformation. The results indicate that the calculated deformation aligns well with field observations, revealing that certain portions of the slope remain in a stress adjustment phase. The predicted deformation convergence is expected between 2025 and 2036, with stabilization occurring between 2034 and 2039, and an ultimate deformation ranging from 165 to 215 mm.