Downscaling GRACE TWSA Data into High-Resolution Groundwater Level Anomaly Using Machine Learning-Based Models in a Glacial Aquifer System

With continued threat from climate change and human impacts, high-resolution and continuous hydrologic data accessibility has a paramount importance for predicting trends and availability of water resources. This study presents a novel machine learning (ML)-based downscaling algorithm that produces a high spatial resolution groundwater level anomaly (GWLA) from the Gravity Recovery and Climate Experiment (GRACE) data by utilizing the relationship between Terrestrial Water Storage Anomaly (TWSA) from GRACE and other land surface and hydro-climatic variables (e.g., vegetation coverage, land surface temperature, precipitation, streamflow, and in-situ groundwater level data). The predicted downscaled GWLA data were tested using monthly in-situ groundwater level observations. Of the 32 groundwater monitoring wells available in the study site, 21 wells were used to develop the ML-based downscaling model, while the remaining 11 wells were used to assess the performance of the ML-based downscaling model. The test results showed that the model satisfactorily reproduces the spatial and temporal variation of the GWLA in the area, with acceptable correlation coefficient and Nash-Sutcliffe Efficiency values of ~0.76 and ~0.45, respectively. GRACE TWSA was the most influential predictor variable in the models, followed by stream discharge and soil moisture storage. Though model limitations and uncertainty could exist due to high spatial heterogeneity of the geologic materials and omission of human impact (e.g., abstraction), the significance of the result is undeniable, particularly in areas where in-situ well measurements are sparse.

[1]  A. Milewski,et al.  A quantitative assessment of groundwater resources in the Middle East and North Africa region , 2018, Hydrogeology Journal.

[2]  Russell G. Congalton,et al.  Evaluating the potential for measuring river discharge from space , 2003 .

[3]  Wilfried Brutsaert,et al.  Long‐term groundwater storage trends estimated from streamflow records: Climatic perspective , 2008 .

[4]  Robert M. Hirsch,et al.  Past, Present, and Future of Water Data Delivery from the U.S. Geological Survey , 2014 .

[5]  Helen Bonsor,et al.  Quantitative maps of groundwater resources in Africa , 2012 .

[6]  Aldo V. Vecchia,et al.  waterData--An R package for retrieval, analysis, and anomaly calculation of daily hydrologic time series data, version 1.0 , 2012 .

[7]  N. Muttil,et al.  Rainfall trend and its implications for water resource management within the Yarra River catchment, Australia , 2013 .

[8]  P. Döll,et al.  Global‐scale assessment of groundwater depletion and related groundwater abstractions: Combining hydrological modeling with information from well observations and GRACE satellites , 2014 .

[9]  M. Bierkens,et al.  Global depletion of groundwater resources , 2010 .

[10]  J. Kusche,et al.  Calibration/Data Assimilation Approach for Integrating GRACE Data into the WaterGAP Global Hydrology Model (WGHM) Using an Ensemble Kalman Filter: First Results , 2013, Surveys in Geophysics.

[11]  Mohamed Sultan,et al.  RESDEM, a tool for integrating temporal remote sensing data for use in hydrogeologic investigations , 2009, Comput. Geosci..

[12]  M. Watkins,et al.  The gravity recovery and climate experiment: Mission overview and early results , 2004 .

[13]  Robert M. Hirsch,et al.  User guide to Exploration and Graphics for RivEr Trends (EGRET) and dataRetrieval: R packages for hydrologic data , 2015 .

[14]  Eric F. Wood,et al.  Predicting the Discharge of Global Rivers , 2001, Journal of Climate.

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

[16]  L. Longuevergne,et al.  Recent changes in terrestrial water storage in the Upper Nile Basin: an evaluation of commonly used gridded GRACE products , 2017 .

[17]  Adam Milewski,et al.  Monitoring and comparison of terrestrial water storage changes in the northern high plains using GRACE and in-situ based integrated hydrologic model estimates , 2016 .

[18]  J Elith,et al.  A working guide to boosted regression trees. , 2008, The Journal of animal ecology.

[19]  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.

[20]  Simon J. Hook,et al.  Intercomparison of versions 4, 4.1 and 5 of the MODIS Land Surface Temperature and Emissivity products and validation with laboratory measurements of sand samples from the Namib desert, Namibia , 2009 .

[21]  Wondwosen M. Seyoum,et al.  Understanding the relative impacts of natural processes and human activities on the hydrology of the Central Rift Valley lakes, East Africa , 2015 .

[22]  Younggu Her,et al.  SWAT+ versus SWAT2012: Comparison of sub-daily urban runoff simulations , 2018 .

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

[24]  J. Famiglietti,et al.  Improving parameter estimation and water table depth simulation in a land surface model using GRACE water storage and estimated base flow data , 2010 .

[25]  Zhangli Sun,et al.  Assessing Terrestrial Water Storage and Flood Potential Using GRACE Data in the Yangtze River Basin, China , 2017, Remote. Sens..

[26]  A. Milewski,et al.  Improved methods for estimating local terrestrial water dynamics from GRACE in the Northern High Plains. , 2017 .

[27]  James S. Famiglietti,et al.  Downscaling GRACE Remote Sensing Datasets to High-Resolution Groundwater Storage Change Maps of California's Central Valley , 2018, Remote. Sens..

[28]  Jerome H Friedman,et al.  Multiple additive regression trees with application in epidemiology , 2003, Statistics in medicine.

[29]  Sharon L. Qi,et al.  Maps and grids of hydrogeologic information created from standardized water-well drillers’ records of the glaciated United States , 2017 .

[30]  J. Friedman Greedy function approximation: A gradient boosting machine. , 2001 .

[31]  S. Swenson,et al.  Post‐processing removal of correlated errors in GRACE data , 2006 .

[32]  Y. Hong,et al.  The TRMM Multisatellite Precipitation Analysis (TMPA): Quasi-Global, Multiyear, Combined-Sensor Precipitation Estimates at Fine Scales , 2007 .

[33]  W. Seyoum Characterizing water storage trends and regional climate influence using GRACE observation and satellite altimetry data in the Upper Blue Nile River Basin , 2018, Journal of Hydrology.

[34]  Shuanggen Jin,et al.  Lake level change and total water discharge in East Africa Rift Valley from satellite-based observations , 2014, GPC 2014.

[35]  Jie Wang,et al.  Temporal Evolution of Regional Drought Detected from GRACE TWSA and CCI SM in Yunnan Province, China , 2017, Remote. Sens..

[36]  C. K. Shum,et al.  Characterization of terrestrial water dynamics in the Congo Basin using GRACE and satellite radar altimetry , 2011 .

[37]  A. Milewski,et al.  The groundwater risk index: Development and application in the Middle East and North Africa region. , 2018, The Science of the total environment.

[38]  J. Famiglietti,et al.  A GRACE‐based water storage deficit approach for hydrological drought characterization , 2014 .

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

[40]  W. Kelly,et al.  Recharge and Groundwater Flow Within an Intracratonic Basin, Midwestern United States , 2018, Ground water.

[41]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

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

[43]  R. Bergstrom,et al.  Glacial drift in Illinois : thickness and character , 1967 .

[44]  Guillaume Favreau,et al.  Remote sensing for groundwater modelling in large semiarid areas: Lake Chad Basin, Africa , 2007 .

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

[46]  Alexander Y. Sun,et al.  Using GRACE Satellite Gravimetry for Assessing Large-Scale Hydrologic Extremes , 2017, Remote. Sens..

[47]  F. Aires,et al.  Surface freshwater storage and variability in the Amazon basin from multi‐satellite observations, 1993–2007 , 2013 .

[48]  Z. Wan New refinements and validation of the MODIS Land-Surface Temperature/Emissivity products , 2008 .

[49]  B. Bouman,et al.  Field water management to save water and increase its productivity in irrigated lowland rice , 2001 .

[50]  H. Toniolo,et al.  Hydrologic Modeling of Three Sub-Basins in the Kenai River Watershed, Alaska, USA , 2018 .

[51]  Byron D. Tapley,et al.  The 2009 exceptional Amazon flood and interannual terrestrial water storage change observed by GRACE , 2010 .

[52]  Robert E. Schapire,et al.  The Boosting Approach to Machine Learning An Overview , 2003 .