Exploiting Earth Observation Data to Impute Groundwater Level Measurements with an Extreme Learning Machine

Groundwater resources are expensive to develop and use; they are difficult to monitor and data collected from monitoring wells are often sporadic, often only available at irregular, infrequent, or brief intervals. Groundwater managers require an accurate understanding of historic groundwater storage trends to effectively manage groundwater resources, however, most if not all well records contain periods of missing data. To understand long-term trends, these missing data need to be imputed before trend analysis. We present a method to impute missing data at single wells, by exploiting data generated from Earth observations that are available globally. We use two soil moisture models, the Global Land Data Assimilation System (GLDAS) model and National Oceanic and Atmospheric Administration (NOAA) Climate Prediction Center (CPC) soil moisture model to impute the missing data. Our imputation method uses a machine learning technique called Extreme Learning Machine (ELM). Our implementation uses 11 input data-streams, all based on Earth observation data. We train and apply the model one well at a time. We selected ELM because it is a single hidden layer feedforward model that can be trained quickly on minimal data. We tested the ELM method using data from monitoring wells in the Cedar Valley and Beryl-Enterprise areas in southwest Utah, USA. We compute error estimates for the imputed data and show that ELM-computed estimates were more accurate than Kriging estimates. This ELM-based data imputation method can be used to impute missing data at wells. These complete time series can be used improve the accuracy of aquifer groundwater elevation maps in areas where in-situ well measurements are sparse, resulting in more accurate spatial estimates of the groundwater surface. The data we use are available globally from 1950 to the present, so this method can be used anywhere in the world.

[1]  Steven Evans Groundwater Level Mapping Tool: Development of a Web Application to Effectively Characterize Groundwater Resources , 2019 .

[2]  Todd K. Moon,et al.  A comparison of data imputation methods using Bayesian compressive sensing and Empirical Mode Decomposition for environmental temperature data , 2018, Environ. Model. Softw..

[3]  Hua-Liang Wei,et al.  Handling missing data in multivariate time series using a vector autoregressive model-imputation (VAR-IM) algorithm , 2018, Neurocomputing.

[4]  Nathan R. Swain,et al.  Simplifying the deployment of OGC web processing services (WPS) for environmental modelling - Introducing Tethys WPS Server , 2019, Environ. Model. Softw..

[5]  Eva Boegh,et al.  Evaluating evapotranspiration rates and surface conditions using Landsat TM to estimate atmospheric resistance and surface resistance , 2002 .

[6]  Li-Chiu Chang,et al.  Prediction of monthly regional groundwater levels through hybrid soft-computing techniques , 2016 .

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

[8]  John Kaiser Calautit,et al.  A review of artificial neural network models for ambient air pollution prediction , 2019, Environ. Model. Softw..

[9]  Patrick Hostert,et al.  Differences in Landsat-based trend analyses in drylands due to the choice of vegetation estimate , 2011 .

[10]  Shahrokh Rouhani,et al.  Multivariate geostatistical approach to space‐time data analysis , 1990 .

[11]  M. Ehteshami,et al.  Simulation and analysis of temporal changes of groundwater depth using time series modeling , 2016, Modeling Earth Systems and Environment.

[12]  Steven J. Burian,et al.  A new open source platform for lowering the barrier for environmental web app development , 2016, Environ. Model. Softw..

[13]  M. Mirzavand,et al.  A Stochastic Modelling Technique for Groundwater Level Forecasting in an Arid Environment Using Time Series Methods , 2015, Water Resources Management.

[14]  C. Karavitis,et al.  A novel framework for filling data gaps in groundwater level observations , 2018, Advances in Water Resources.

[15]  G. Carbone,et al.  Monitoring agricultural drought for arid and humid regions using multi-sensor remote sensing data , 2010 .

[16]  Gustavious P. Williams,et al.  Hydrostats: A Python Package for Characterizing Errors between Observed and Predicted Time Series , 2018, Hydrology.

[17]  Madan K. Jha,et al.  Groundwater-level prediction using multiple linear regression and artificial neural network techniques: a comparative assessment , 2013, Hydrogeology Journal.

[18]  竹安 数博,et al.  Time series analysis and its applications , 2007 .

[19]  R. D. Ramsey,et al.  Evaluating the Use of Landsat 30m Enhanced Thematic Mapper to Monitor Vegetation Cover in Shrub‐Steppe Environments , 2004 .

[20]  Jun Miao,et al.  Constrained Extreme Learning Machine: A novel highly discriminative random feedforward neural network , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

[21]  Omesaad Rado,et al.  Performance Analysis of Missing Values Imputation Methods Using Machine Learning Techniques , 2019, Advances in Intelligent Systems and Computing.

[22]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[23]  Daniel P. Ames,et al.  Introductory overview: Error metrics for hydrologic modelling - A review of common practices and an open source library to facilitate use and adoption , 2019, Environ. Model. Softw..

[24]  Xu Zhou,et al.  Effective algorithms of the Moore-Penrose inverse matrices for extreme learning machine , 2015, Intell. Data Anal..

[25]  K. Moffett,et al.  Remote Sens , 2015 .

[26]  H. V. D. Dool,et al.  A global monthly land surface air temperature analysis for 1948-present , 2008 .

[27]  Guang-Bin Huang,et al.  What are Extreme Learning Machines? Filling the Gap Between Frank Rosenblatt’s Dream and John von Neumann’s Puzzle , 2015, Cognitive Computation.

[28]  Thomas J. Jackson,et al.  Remote sensing of soil moisture: implications for groundwater recharge , 2002 .

[29]  Huug van den Dool,et al.  Analysis of model-calculated soil moisture over the United States (1931-1993) and applications to long-range temperature forecasts , 1996 .

[30]  Jeffrey P. Walker,et al.  THE GLOBAL LAND DATA ASSIMILATION SYSTEM , 2004 .

[31]  V. J. Bidwell,et al.  Realistic forecasting of groundwater level, based on the eigenstructure of aquifer dynamics , 2005, Math. Comput. Simul..

[32]  Huan Wang,et al.  A Comparative Study of Artificial Neural Networks, Support Vector Machines and Adaptive Neuro Fuzzy Inference System for Forecasting Groundwater Levels near Lake Okeechobee, Florida , 2015, Water Resources Management.

[33]  Skipper Seabold,et al.  Statsmodels: Econometric and Statistical Modeling with Python , 2010, SciPy.

[34]  G. Williams,et al.  An Empirical Mode-Spatial Model for Environmental Data Imputation , 2018, Hydrology.

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

[36]  Saleh M. Al-Alawi,et al.  Combining principal component regression and artificial neural networks for more accurate predictions of ground-level ozone , 2008, Environ. Model. Softw..

[37]  J. Janowiak,et al.  Global Land Precipitation: A 50-yr Monthly Analysis Based on Gauge Observations , 2002 .

[38]  Gaël Varoquaux,et al.  The NumPy Array: A Structure for Efficient Numerical Computation , 2011, Computing in Science & Engineering.

[39]  鈴木 和美,et al.  Palmer Drought Severity Index(PDSI)を用いたモンゴルの旱魃の解析 , 2004 .

[40]  Michael Piasecki,et al.  Availability and coverage of hydrologic data in the US geological survey National Water Information System (NWIS) and US Environmental Protection Agency Storage and Retrieval System (STORET) , 2008, Earth Sci. Informatics.

[41]  M. H. Quenouille Approximate tests of correlation in time-series 3 , 1949, Mathematical Proceedings of the Cambridge Philosophical Society.

[42]  Nathan R. Swain Tethys: A Platform for Water Resources Modeling and Decision Support Apps , 2014 .

[43]  Elahe Fallah-Mehdipour,et al.  Prediction and simulation of monthly groundwater levels by genetic programming , 2013 .

[44]  B. Marchant,et al.  Spatio-temporal modelling of the status of groundwater droughts , 2018, Journal of Hydrology.

[45]  J. Rogan,et al.  Remote sensing technology for mapping and monitoring land-cover and land-use change , 2004 .

[46]  R. E. Carlson,et al.  Monotone Piecewise Cubic Interpolation , 1980 .

[47]  Joel Nothman,et al.  SciPy 1.0-Fundamental Algorithms for Scientific Computing in Python , 2019, ArXiv.

[48]  Yi-Bo Luo,et al.  Evaluating the performance of remote sensing precipitation products CMORPH, PERSIANN, and TMPA, in the arid region of northwest China , 2014, Theoretical and Applied Climatology.

[49]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[50]  J. Dozier,et al.  Inroads of remote sensing into hydrologic science during the WRR era , 2015 .

[51]  Wes McKinney,et al.  Data Structures for Statistical Computing in Python , 2010, SciPy.

[52]  Robert H. Shumway,et al.  Time series analysis and its applications : with R examples , 2017 .

[53]  W. Wagner,et al.  Evaluation of the agreement between the first global remotely sensed soil moisture data with model and precipitation data , 2003 .