Downscaling GRACE Remote Sensing Datasets to High-Resolution Groundwater Storage Change Maps of California's Central Valley

NASA’s Gravity Recovery and Climate Experiment (GRACE) has already proven to be a powerful data source for regional groundwater assessments in many areas around the world. However, the applicability of GRACE data products to more localized studies and their utility to water management authorities have been constrained by their limited spatial resolution (~200,000 km2). Researchers have begun to address these shortcomings with data assimilation approaches that integrate GRACE-derived total water storage estimates into complex regional models, producing higher-resolution estimates of hydrologic variables (~2500 km2). Here we take those approaches one step further by developing an empirically based model capable of downscaling GRACE data to a high-resolution (~16 km2) dataset of groundwater storage changes over a portion of California’s Central Valley. The model utilizes an artificial neural network to generate a series of high-resolution maps of groundwater storage change from 2002 to 2010 using GRACE estimates of variations in total water storage and a series of widely available hydrologic variables (PRISM precipitation and temperature data, digital elevation model (DEM)-derived slope, and Natural Resources Conservation Service (NRCS) soil type). The neural network downscaling model is able to accurately reproduce local groundwater behavior, with acceptable Nash-Sutcliffe efficiency (NSE) values for calibration and validation (ranging from 0.2445 to 0.9577 and 0.0391 to 0.7511, respectively). Ultimately, the model generates maps of local groundwater storage change at a 100-fold higher resolution than GRACE gridded data products without the use of computationally intensive physical models. The model’s simulated maps have the potential for application to local groundwater management initiatives in the region.

[1]  Andreas Güntner,et al.  Improvement of Global Hydrological Models Using GRACE Data , 2008 .

[2]  Young-Seuk Park,et al.  The application of Artificial Neural Network (ANN) model to the simulation of denitrification rates in mesocosm-scale wetlands , 2013, Ecol. Informatics.

[3]  J. Delhomme.  Kriging in the hydrosciences , 1978 .

[4]  S. Swenson,et al.  Uncertainty in global groundwater storage estimates in a Total Groundwater Stress framework , 2015, Water resources research.

[5]  S. Swenson,et al.  Satellites measure recent rates of groundwater depletion in California's Central Valley , 2011 .

[6]  Matthew Rodell,et al.  Groundwater depletion in the Middle East from GRACE with implications for transboundary water management in the Tigris-Euphrates-Western Iran region , 2013, Water resources research.

[7]  S. Charles,et al.  Comparison of runoff modelled using rainfall from different downscaling methods for historical and future climates , 2010 .

[8]  R. Mehrotra,et al.  A comparison of multi-site daily rainfall downscaling techniques under Australian conditions , 2011 .

[9]  M. Gevrey,et al.  Review and comparison of methods to study the contribution of variables in artificial neural network models , 2003 .

[10]  J. Kusche,et al.  Separation of large scale water storage patterns over Iran using GRACE, altimetry and hydrological data , 2014 .

[11]  Mazda Kompani-Zare,et al.  Groundwater depth and elevation interpolation by kriging methods in Mohr Basin of Fars province in Iran , 2010, Environmental monitoring and assessment.

[12]  Yue Sun,et al.  Comparison of interpolation methods for depth to groundwater and its temporal and spatial variations in the Minqin oasis of northwest China , 2009, Environ. Model. Softw..

[13]  S. Lek,et al.  The use of artificial neural networks to assess fish abundance and spatial occupancy in the littoral zone of a mesotrophic lake , 1999 .

[14]  Long Jin,et al.  Precipitation Prediction Modeling using Neural Network and Empirical Orthogonal Function Base on Numerical Weather Forecast Production , 2006, 2006 6th World Congress on Intelligent Control and Automation.

[15]  S. Pryor,et al.  Downscaling temperature and precipitation: a comparison of regression‐based methods and artificial neural networks , 2001 .

[16]  R. Johnston,et al.  Ground water in the Central Valley, California; a summary report , 1991 .

[17]  Taha B. M. J. Ouarda,et al.  Spatial Bayesian Model for Statistical Downscaling of AOGCM to Minimum and Maximum Daily Temperatures , 2010 .

[18]  J. Elliott,et al.  Machine learning algorithms for modeling groundwater level changes in agricultural regions of the U.S. , 2017 .

[19]  W. Feng,et al.  Evaluation of groundwater depletion in North China using the Gravity Recovery and Climate Experiment (GRACE) data and ground‐based measurements , 2013 .

[20]  P. Martin,et al.  Modeling a Complex Multi‐Aquifer System: The Waterloo Moraine , 1998 .

[21]  S. Swenson,et al.  Quantifying renewable groundwater stress with GRACE , 2015, Water resources research.

[22]  Y. R. Satyaji Rao,et al.  Modelling groundwater levels in an urban coastal aquifer using artificial neural networks , 2008 .

[23]  T. Wigley,et al.  Downscaling general circulation model output: a review of methods and limitations , 1997 .

[24]  Paulin Coulibaly,et al.  Temporal neural networks for downscaling climate variability and extremes , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[25]  B. Scanlon,et al.  Comparison of seasonal terrestrial water storage variations from GRACE with groundwater‐level measurements from the High Plains Aquifer (USA) , 2007 .

[26]  P. Whetton,et al.  Guidelines for Use of Climate Scenarios Developed from Statistical Downscaling Methods , 2004 .

[27]  B. Minsker,et al.  Cost‐effective long‐term groundwater monitoring design using a genetic algorithm and global mass interpolation , 2000 .

[28]  James S. Famiglietti,et al.  Irrigation in California's Central Valley strengthens the southwestern U.S. water cycle , 2013 .

[29]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[30]  James P. Hughes,et al.  Data requirements for kriging: Estimation and network design , 1981 .

[31]  C. Faunt,et al.  Water availability and land subsidence in the Central Valley, California, USA , 2016, Hydrogeology Journal.

[32]  W. Kinzelbach,et al.  Real‐time groundwater flow modeling with the Ensemble Kalman Filter: Joint estimation of states and parameters and the filter inbreeding problem , 2008 .

[33]  J. Famiglietti,et al.  Characteristic mega-basin water storage behavior using GRACE , 2013, Water resources research.

[34]  F. LeMoine,et al.  Resolving mass flux at high spatial and temporal resolution using GRACE intersatellite measurements , 2005 .

[35]  Rajandrea Sethi,et al.  Artificial neural network simulation of hourly groundwater levels in a coastal aquifer system of the Venice lagoon , 2012, Eng. Appl. Artif. Intell..

[36]  Amy J. Ruggles,et al.  An Experimental Comparison of Ordinary and Universal Kriging and Inverse Distance Weighting , 1999 .

[37]  Julian D. Olden,et al.  Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks , 2002 .

[38]  J. Famiglietti,et al.  Estimating groundwater storage changes in the Mississippi River basin (USA) using GRACE , 2007 .

[39]  Jeffrey G. Arnold,et al.  Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations , 2007 .

[40]  M. Rodell,et al.  Assimilation of GRACE Terrestrial Water Storage Data into a Land Surface Model: Results for the Mississippi River Basin , 2008 .

[41]  Richard D. Robarts,et al.  Time for in situ renaissance , 2015, Science.

[42]  T. Wigley,et al.  Statistical downscaling of general circulation model output: A comparison of methods , 1998 .

[43]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[44]  Paulin Coulibaly,et al.  Groundwater level forecasting using artificial neural networks , 2005 .

[45]  A. Zhu.  Mapping soil landscape as spatial continua: The Neural Network Approach , 2000 .

[46]  Matthew Rodell,et al.  The potential for satellite-based monitoring of groundwater storage changes using GRACE: the High Plains aquifer, Central US , 2002 .

[47]  Vijay P. Singh,et al.  Assessment of Informativeness of Groundwater Monitoring in Developing Regions (Gaza Strip Case Study) , 2005 .

[48]  William M. Alley,et al.  Bringing GRACE Down to Earth , 2015, Ground water.

[49]  J. Famiglietti,et al.  Satellite-based estimates of groundwater depletion in India , 2009, Nature.

[50]  Martha C. Anderson,et al.  Precipitation Estimation from Remotely Sensed Information Using Articial Neural Networks , 2012 .

[51]  Liang-Cheng Chang,et al.  Optimal control algorithm and neural network for dynamic groundwater management , 2009 .

[52]  Ping Li,et al.  Application and comparison of two prediction models for groundwater levels: a case study in Western Jilin Province, China. , 2009 .

[53]  G. Dagan.  Stochastic modeling of groundwater flow by unconditional and conditional probabilities: 1. Conditional simulation and the direct problem , 1982 .

[54]  Alexander Y. Sun,et al.  Predicting groundwater level changes using GRACE data , 2013 .

[55]  Zakari Arétouyap,et al.  Lessening the adverse effect of the semivariogram model selection on an interpolative survey using kriging technique , 2016, SpringerPlus.

[56]  Alex J. Cannon,et al.  Downscaling recent streamflow conditions in British Columbia, Canada using ensemble neural network models , 2002 .

[57]  F. Landerer,et al.  Accuracy of scaled GRACE terrestrial water storage estimates , 2012 .

[58]  S. Lallahem,et al.  On the use of neural networks to evaluate groundwater levels in fractured media , 2005 .

[59]  Hayley J. Fowler,et al.  Linking climate change modelling to impacts studies: recent advances in downscaling techniques for hydrological modelling , 2007 .

[60]  K. Lee,et al.  A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer , 2011 .

[61]  J. Schoof.  Statistical Downscaling in Climatology , 2013 .

[62]  J. Kusche,et al.  Improving drought simulations within the Murray-Darling Basin by combined calibration/assimilation of GRACE data into the WaterGAP Global Hydrology Model , 2018 .

[63]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[64]  E. G. Vomvoris,et al.  A geostatistical approach to the inverse problem in groundwater modeling (steady state) and one‐dimensional simulations , 1983 .

[65]  J. Famiglietti.  The global groundwater crisis , 2014 .

[66]  Kuolin Hsu,et al.  Artificial Neural Network Modeling of the Rainfall‐Runoff Process , 1995 .

[67]  Taher Rajaee,et al.  Simulation of groundwater level variations using wavelet combined with neural network, linear regression and support vector machine , 2017 .

[68]  Witold F. Krajewski,et al.  Rainfall forecasting in space and time using a neural network , 1992 .

[69]  S. Sorooshian,et al.  Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks , 1997 .

[70]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

[71]  A. Cazenave,et al.  Using GRACE to detect Groundwater Storage variations: the cases of Canning Basin and Guarani Aquifer System , 2012 .

[72]  A. Hall,et al.  Downscaling near-surface wind over complex terrain using a physically-based statistical modeling approach , 2013, Climate Dynamics.

[73]  S. Swenson,et al.  Remote sensing of groundwater storage changes in Illinois using the Gravity Recovery and Climate Experiment (GRACE) , 2006 .

[74]  M. Rodell,et al.  Water in the Balance , 2013, Science.

[75]  Jennifer L. Shelton,et al.  Hydrogeologic characterization of the Modesto Area, San Joaquin Valley, California , 2004 .