Surrogate optimization of deep neural networks for groundwater predictions

Sustainable management of groundwater resources under changing climatic conditions require an application of reliable and accurate predictions of groundwater levels. Mechanistic multi-scale, multi-physics simulation models are often too hard to use for this purpose, especially for groundwater managers who do not have access to the complex compute resources and data. Therefore, we analyzed the applicability and performance of four modern deep learning computational models for predictions of groundwater levels. We compare three methods for optimizing the models’ hyperparameters, including two surrogate model-based algorithms and a random sampling method. The models were tested using predictions of the groundwater level in Butte County, California, USA, taking into account the temporal variability of streamflow, precipitation, and ambient temperature. Our numerical study shows that the optimization of the hyperparameters can lead to reasonably accurate performance of all models (root mean squared errors of groundwater predictions of 2 meters or less), but the “simplest” network, namely a multilayer perceptron (MLP) performs overall better for learning and predicting groundwater data than the more advanced long short-term memory or convolutional neural networks in terms of prediction accuracy and time-to-solution, making the MLP a suitable candidate for groundwater prediction.

     

Washboards in unpaved highways as a complex dynamic system

We present a new model and results for simulation of washboards, or corrugations, in unpaved highways. Our review of published literature shows that the washboard phenomenon on unpaved highways is the result of dynamic interaction between vehicle wheels and road surface, affected by a number of nonlinear variables in the physical system. Rather than attempt to solve the system analytically, we define a set of simple, locally defined rules to describe (1) the wheel jump upon striking an irregularity on the roadway surface and (2) the resulting digging. We use a computer simulation to iterate a mapping algorithm to simulate the effect of multiple vehicles. Finally, we analyze the resulting simulated road surfaces for evidence of complexity using information entropy and chaotic analysis. This approach is able to explain several outstanding questions in the literature, including the irregularity of washboard geometry, the direction of washboard migration, and the determination of washboard pitch, or wavelength. The study also resulted in several observations that are commonly associated with complex dynamic systems, including pattern emergence, sensitive dependence on initial conditions, and for some simulations, evidence of spatial chaos. Our conclusion is that washboards in unpaved highways may be modeled as the manifestation of a complex dynamical system. © 2000 John Wiley & Sons, Inc.Complexity 5: 51‐60, 2000