Modeling of soil behavior with a recurrent neural network

A recurrent neural network (RNN) model is developed for simulating and pred icting shear behavior of both a fine-grained residual soil and a dune sand. The RNN model with one hidden layer of 20 nodes appears very effective in modeling complex soil behavior, due to its feedback connections from a hidd en layer to an input layer. A dynamic gradient descent learning algorithm i s used to train the network. By training part of the experimental data, whi ch include strain-controlled undrained tests and stress-controlled drained tests performed on a residual Hawaiian volcanic soil, the network is able t o capture significant variability of shear behavior existing in the residua l soil. The unusual characteristics that the denser soil samples dilate und er a higher stress level and the looser soil samples contract under a lower stress level are well represented by the RNN model. The RNN model also sho ws encouraging results in simulation and prediction of behavior of a dune s and which experienced loading-unloading-reloading conditions. Excellent agr eements between the measured data and the modeling results are observed in both stress-strain behavior and volumetric-change characteristics. As compa red with a traditional model, the RNN model shows more effectiveness and le ss effort.