Surrogate modeling for unsaturated infiltration via the physics and equality-constrained artificial neural networks

Machine learning(ML)provides a new surrogate method for investigating groundwater flow dynamics in unsaturated soils.Traditional pure data-driven methods(e.g.deep neural network,DNN)can provide rapid predictions,but they do require sufficient on-site data for accurate training,and lack interpretability to the physical processes within the data.In this paper,we provide a physics and equalityconstrained artificial neural network(PECANN),to derive unsaturated infiltration solutions with a small amount of initial and boundary data.PECANN takes the physics-informed neural network(PINN)as a foundation,encodes the unsaturated infiltration physical laws(i.e.Richards equation,RE)into the loss function,and uses the augmented Lagrangian method to constrain the learning process of the solutions of RE by adding stronger penalty for the initial and boundary conditions.Four unsaturated infiltration cases are designed to test the training performance of PECANN,i.e.one-dimensional(1D)steady-state unsaturated infiltration,1D transient-state infiltration,two-dimensional(2D)transient-state infiltration,and 1D coupled unsaturated infiltration and deformation.The predicted results of PECANN are compared with the finite difference solutions or analytical solutions.The results indicate that PECANN can accurately capture the variations of pressure head during the unsaturated infiltration,and present higher precision and robustness than DNN and PINN.It is also revealed that PECANN can achieve the same accuracy as the finite difference method with fewer initial and boundary training data.Additionally,we investigate the effect of the hyperparameters of PECANN on solving RE problem.PECANN provides an effective tool for simulating unsaturated infiltration.

Stability analysis of an unsaturated soil slope considering rainfall infiltration based on the Green-Ampt model

Based on the principle of saturated infiltration and the Green-Ampt model,an unsaturated infiltration model for a soil slope surface was established for either constant moisture content,or depth-varying moisture content and the slope.Infiltration parameters in the partially saturated slope were revealed under sustained rainfall.Through analysis of the variation of initial moisture content in the slope,the ponding time,infiltration depth,and infiltration rate were deduced for an unsaturated soil slope subject to rainfall infiltration.There is no ponded water on the surface of the slope under sustained low-intensity rainfall.The results show that the infiltration parameters of an unsaturated slope are influenced by the initial moisture content and the wetting front saturation,the soil cohesion and rainfall intensity under sustained rainfall.More short-term slope failures can occur with the decrease of cohesion of the soil of the slope.The ponding time and infiltration depth differ considering constant or different initial moisture content respectively in the soil slope.Then,best-fit curves of the infiltration rate,ponding time,and infiltration depth to the wetting front saturation were obtained with constant or different initial moisture contents.And the slope failure time is roughly uniform when subject to a rainfall intensity I>5 mm/h.

The Unsaturated Hydraulic Parameters for Aeolian Sand

The water characteristic curve for aeolian sand in two processes of wetting and drying was obtained by the negative water column technique.The values of fitting parameters were calculated according to Van Genuchten formula and the parameters that characterized the prosperities of aeolian sand such as the unsaturated infiltration coefficient and specific water capacity were obtained.The results showed that the water characteristic curve for aeolian sand in wetting process had greater hysteresis quality than ...