Abstract
Abstract. An integrated space–time artificial neural network (ANN) model inspired by the governing groundwater flow equation was developed to test whether a single ANN is capable of modeling regional groundwater flow systems. Model-independent entropy measures and random forest (RF)-based feature selection procedures were used to identify suitable inputs for ANNs. L2 regularization, five-fold cross-validation, and an adaptive stochastic gradient descent (ADAM) algorithm led to a parsimonious ANN model for a 30 691 km2 agriculturally intensive area in the Ogallala Aquifer of Texas. The model testing at 38 independent wells during the 1956–2008 calibration period showed no overfitting issues and highlighted the model's ability to capture both the observed spatial dependence and temporal variability. The forecasting period (2009–2015) was marked by extreme climate variability in the region and served to evaluate the extrapolation capabilities of the model. While ANN models are universal interpolators, the model was able to capture the general trends and provide groundwater level estimates that were better than using historical means. Model sensitivity analysis indicated that pumping was the most sensitive process. Incorporation of spatial variability was more critical than capturing temporal persistence. The use of the standardized precipitation–evapotranspiration index (SPEI) as a surrogate for pumping was generally adequate but was unable to capture the heterogeneous groundwater extraction preferences of farmers under extreme climate conditions.
Highlights
There is a growing recognition that alternative, data-driven model formulations can be employed to better capture nonlinear aquifer response dynamics (Obergfell et al, 2019; Roshni et al, 2019; Rinderer et al, 2018; Adamowski and Chan, 2011; Daliakopoulos et al, 2005)
While forecasting water levels at individual wells is sufficient in certain groundwater applications, capturing the spatiotemporal dynamics of groundwater levels is critical for regional-scale aquifer management
The primary goal of this study is to test this hypothesis by constructing a single space–time artificial neural network (ANN) model to capture the spatiotemporal variability in groundwater levels noted within a region
Summary
There is a growing recognition that alternative, data-driven model formulations can be employed to better capture nonlinear aquifer response dynamics (Obergfell et al, 2019; Roshni et al, 2019; Rinderer et al, 2018; Adamowski and Chan, 2011; Daliakopoulos et al, 2005). While forecasting water levels at individual wells is sufficient in certain groundwater applications, capturing the spatiotemporal dynamics of groundwater levels is critical for regional-scale aquifer management. While regional groundwater flow models continue to be developed using physically based methods that integrate conservation principles and Darcy’s law (Anderson et al, 2015; Harbaugh, 2005), attempts have been made to capture spatiotemporal groundwater behavior using ANNs (Sahoo et al, 2017a, b; Tapoglou et al, 2014; Nourani et al, 2011, 2008). Spatiotemporal modeling of groundwater levels using ANNs is often carried out using a two-stage process. Separate ANN models are constructed at individual wells where groundwater level time series data are available. Forecasts from these individual wells are regionalized using statistical and geostatistical
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
