DOI: 10.5194/hess-24-5759-2020
论文题名: Physics-inspired integrated space-time artificial neural networks for regional groundwater flow modeling
作者: Ghaseminejad A. ; Uddameri V.
刊名: Hydrology and Earth System Sciences
ISSN: 1027-5606
出版年: 2020
卷: 24, 期: 12 起始页码: 5759
结束页码: 5779
语种: 英语
Scopus关键词: Ability testing
; Aquifers
; Climate models
; Decision trees
; Gradient methods
; Groundwater flow
; Groundwater resources
; Sensitivity analysis
; Stochastic models
; Stochastic systems
; Well testing
; Artificial neural network models
; Groundwater extraction
; Groundwater flow equation
; Model sensitivity analysis
; Regional groundwater flow
; Regional groundwater flow modeling
; Stochastic gradient descent
; Temporal variability
; Neural networks
; algorithm
; artificial neural network
; entropy
; evapotranspiration
; flow modeling
; groundwater flow
; precipitation assessment
; pumping
; sensitivity analysis
; temporal analysis
; Ogallala Aquifer
; Texas
; United States
英文摘要: 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. Modelindependent 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. © 2020 Author(s). Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/162531
Appears in Collections: 气候变化与战略
There are no files associated with this item.
作者单位: Ghaseminejad, A., Department of Civil, Environmental and Construction Engineering, Texas Tech University, Lubbock, TX 79409, United States; Uddameri, V., Department of Civil, Environmental and Construction Engineering, Texas Tech University, Lubbock, TX 79409, United States
Recommended Citation:
Ghaseminejad A.,Uddameri V.. Physics-inspired integrated space-time artificial neural networks for regional groundwater flow modeling[J]. Hydrology and Earth System Sciences,2020-01-01,24(12)