TY - JOUR
T1 - A Spatially Enhanced Data-Driven Multimodel to Improve Semiseasonal Groundwater Forecasts in the High Plains Aquifer, USA
AU - Amaranto, A.
AU - Munoz-Arriola, F.
AU - Solomatine, D. P.
AU - Corzo, G.
N1 - Funding Information:
The authors acknowledge the support provided by the Robert B. Daugherty Water for Food Global Institute at the University of Nebraska. Some research ideas and components were also developed within the framework of the USDA National Institute of Food and Agriculture, Hatch project NEB-21-166 Accession 1009760 Grant 17-77-30006 of the Russian Science Foundation, and the project Irrigation Sustainability funded by the University of Nebraska-Lincoln's Agriculture Research Division. Post-processed input data and experiments results can be founded in https://github.com/alessandroamaranto/MuMoC. Finally, we appreciate the valuable comments and suggestions made by the reviewers and Maurizio Mazzoleni.
Publisher Copyright:
©2019. The Authors.
PY - 2019
Y1 - 2019
N2 - The aim of this paper is to improve semiseasonal forecast of groundwater availability in response to climate variables, surface water availability, groundwater level variations, and human water management using a two-step data-driven modeling approach. First, we implement an ensemble of artificial neural networks (ANNs) for the 300 wells across the High Plains aquifer (USA). The modeling framework includes a method to choose the most relevant input variables and time lags; an assessment of the effect of exogenous variables on the predictive capabilities of models; and the estimation of the forecast skill based on the Nash-Sutcliffe efficiency (NSE) index, the normalized root mean square error, and the coefficient of determination (R2). Then, for the ANNs with low- accuracy, a MultiModel Combination (MuMoC) based on a hybrid of ANN and an instance-based learning method is applied. MuMoC uses forecasts from neighboring wells to improve the accuracy of ANNs. An exhaustive-search optimization algorithm is employed to select the best neighboring wells based on the cross correlation and predictive accuracy criteria. The results show high average ANN forecasting skills across the aquifer (average NSE > 0.9). Spatially distributed metrics of performance showed also higher error in areas of strong interaction between hydrometeorological forcings, irrigation intensity, and the aquifer. In those areas, the integration of the spatial information into MuMoC leads to an improvement of the model accuracy (NSE increased by 0.12), with peaks higher than 0.3 when the optimization objectives for selecting the neighbors were maximized.tT.
AB - The aim of this paper is to improve semiseasonal forecast of groundwater availability in response to climate variables, surface water availability, groundwater level variations, and human water management using a two-step data-driven modeling approach. First, we implement an ensemble of artificial neural networks (ANNs) for the 300 wells across the High Plains aquifer (USA). The modeling framework includes a method to choose the most relevant input variables and time lags; an assessment of the effect of exogenous variables on the predictive capabilities of models; and the estimation of the forecast skill based on the Nash-Sutcliffe efficiency (NSE) index, the normalized root mean square error, and the coefficient of determination (R2). Then, for the ANNs with low- accuracy, a MultiModel Combination (MuMoC) based on a hybrid of ANN and an instance-based learning method is applied. MuMoC uses forecasts from neighboring wells to improve the accuracy of ANNs. An exhaustive-search optimization algorithm is employed to select the best neighboring wells based on the cross correlation and predictive accuracy criteria. The results show high average ANN forecasting skills across the aquifer (average NSE > 0.9). Spatially distributed metrics of performance showed also higher error in areas of strong interaction between hydrometeorological forcings, irrigation intensity, and the aquifer. In those areas, the integration of the spatial information into MuMoC leads to an improvement of the model accuracy (NSE increased by 0.12), with peaks higher than 0.3 when the optimization objectives for selecting the neighbors were maximized.tT.
KW - artificial neural network
KW - data-driven models
KW - groundwater
KW - irrigation
KW - semi-seasonal forecast
UR - http://www.scopus.com/inward/record.url?scp=85069801851&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85069801851&partnerID=8YFLogxK
U2 - 10.1029/2018WR024301
DO - 10.1029/2018WR024301
M3 - Article
AN - SCOPUS:85069801851
SN - 0043-1397
VL - 55
SP - 5941
EP - 5961
JO - Water Resources Research
JF - Water Resources Research
IS - 7
ER -