Groundwater Level Forecast Via a Discrete Space-State Modelling Approach as a Surrogate to Complex Groundwater Simulation Modelling

Roy, Dilip Kumar; Biswas, Sujit K.; Saha, Kowshik Kumar; Murad, Khandakar Faisal Ibn

doi:10.1007/s11269-021-02787-6

Cited by 15 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where W IR is the well irrigation water demand in m 3 ; A is the crop planning area in km 2 ; ET c is the crop evapotranspiration in mm during the whole growth period of crops; α is the empirical coefficient of effective precipitation and assigned as 0.7 according to the study conducted by Feng et al [36]; P is the precipitation in mm; and β is the coefficient of well irrigation. According to Puyang Water Resources Bulletin, β was assigned as 0.7 for the north and 0.2 for the south.…”

Section: Estimation Of Groundwater Pumpage For Irrigationmentioning

confidence: 99%

“…Groundwater is a dominant water resource in arid and semi-arid areas and widely utilized in various fields of social life [1,2]. Owing to a growing population, fast economic development, and frequent extreme drought events, the demand for water resources has been increasing and, consequently, a large amount of groundwater was over exploited to meet daily water supply [3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Response Characteristics of Shallow Groundwater Level to Hydro-Meteorological Factors and Well Irrigation Water Withdrawals under Different Conditions of Groundwater Buried Depth

Cai

Huang

Xu³

et al. 2022

Water

View full text Add to dashboard Cite

Many irrigation districts along the Yellow River have been suffering shallow groundwater depression and agriculture-use water shortage. For comprehending response relationships of shallow groundwater level and various factors under different conditions of groundwater buried depth, the hydro-meteorological time series and the agricultural production data in Puyang area of Henan Province, China during 2006–2018 were collected for performing wavelet analysis of the relationship between the groundwater level and the four different factors, such as precipitation, air temperature, water stage of the Yellow River, and well irrigation water amount. It is shown that when the burial depth of groundwater varied from 0–10 m to over 10 m, the groundwater level was related with both the precipitation and air temperature from moderately to weakly and the delayed response times of the groundwater level to them extended from 2–4 months to more than 5 months. The groundwater level maintained a medium correlation with the well irrigation water amount as the burial depth increased, but the lag response time of groundwater level to well irrigation dramatically decreased when the burial depth exceeded 10 m. The dynamic response relationship between the groundwater and the water stage of the Yellow River was mainly affected by the distance away from the Yellow River rather than the burial depth and the influence of the river stage on the groundwater level was limited within the distance approximate to 20 km away from the Yellow River. The findings are expected to provide the reference for groundwater level prediction and groundwater resources protection.

show abstract

Section: Estimation Of Groundwater Pumpage For Irrigationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Dynamic Response Characteristics of Shallow Groundwater Level to Hydro-Meteorological Factors and Well Irrigation Water Withdrawals under Different Conditions of Groundwater Buried Depth

Cai

Huang

Xu³

et al. 2022

Water

View full text Add to dashboard Cite

show abstract

“…This near-stationary or regular dynamics allow ANN models, and in particular recurrent neural networks such as the LSTM, to adequately predict the time series, as the output variable becomes increasingly easy to predict as the time series advances. in such conditions, it would be possible to predict the groundwater level of the well P5 by adopting only a univariate prediction approach, which relies solely on the groundwater level observed data as input to the LSTM optimized model (Raghavendra and Deka, 2016;Mohanasundaram et al, 2019;Roy et al, 2021;Sarma and Singh, 2022).…”

Section: Model Performance Assessment Of a Stationary Groundwater Levelmentioning

confidence: 99%

The contribution of remote sensing and input feature selection for groundwater level prediction using LSTM neural networks in the Oum Er-Rbia Basin, Morocco

Bouramtane,

Leblanc,

Kacimi

et al. 2023

Front. Water

View full text Add to dashboard Cite

The planning and management of groundwater in the absence of in situ climate data is a delicate task, particularly in arid regions where this resource is crucial for drinking water supplies and irrigation. Here the motivation is to evaluate the role of remote sensing data and Input feature selection method in the Long Short Term Memory (LSTM) neural network for predicting groundwater levels of five wells located in different hydrogeological contexts across the Oum Er-Rbia Basin (OER) in Morocco: irrigated plain, floodplain and low plateau area. As input descriptive variable, four remote sensing variables were used: the Integrated Multi-satellite Retrievals (IMERGE) Global Precipitation Measurement (GPM) precipitation, Moderate resolution Imaging Spectroradiometer (MODIS) normalized difference vegetation index (NDVI), MODIS land surface temperature (LST), and MODIS evapotranspiration. Three LSTM models were developed, rigorously analyzed and compared. The LSTM-XGB-GS model, was optimized using the GridsearchCV method, and uses a single remote sensing variable identified by the input feature selection method XGBoost. Another optimized LSTM model was also constructed, but uses the four remote sensing variables as input (LSTM-GS). Additionally, a standalone LSTM model was established and also incorporating the four variables as inputs. Scatter plots, violin plots, Taylor diagram and three evaluation indices were used to verify the performance of the three models. The overall result showed that the LSTM-XGB-GS model was the most successful, consistently outperforming both the LSTM-GS model and the standalone LSTM model. Its remarkable accuracy is reflected in high R2 values (0.95 to 0.99 during training, 0.72 to 0.99 during testing) and the lowest RMSE values (0.03 to 0.68 m during training, 0.02 to 0.58 m during testing) and MAE values (0.02 to 0.66 m during training, 0.02 to 0.58 m during testing). The LSTM-XGB-GS model reveals how hydrodynamics, climate, and land-use influence groundwater predictions, emphasizing correlations like irrigated land-temperature link and floodplain-NDVI-evapotranspiration interaction for improved predictions. Finally, this study demonstrates the great support that remote sensing data can provide for groundwater prediction using ANN models in conditions where in situ data are lacking.

show abstract

“…A review of the numerous data‐driven models for simulating the water table elevation is offered in Rajaee et al (2019); the one using the artificial neural network (Banerjee et al, 2009) and discrete space‐state model (Kumar et al, 2021) are cited here as noticeable examples. Such an approach is attractive because of its ability to capture non‐linear trends without prior knowledge on the underlying physical processes due to data limitations.…”

Section: Introductionmentioning

confidence: 99%

Performance of three reanalyses in simulating the water table elevation in different shallow unconfined aquifers in Central Italy

Cerlini

Silvestri

Meniconi

et al. 2023

Meteorological Applications

View full text Add to dashboard Cite

Water table elevation is a key feature for identifying the groundwater behaviour. Accordingly, appropriate measurements—in terms of both frequency and spatial distribution—play a crucial role for capturing the aquifer response to recharge and withdrawals. However, numerical models simulating the main features of the behaviour of the water table elevation may help groundwater management, as an additional tool. In this article, soil moisture data from three well‐established global reanalyses (ERA5, CFS, and JRA‐55) are used for evaluating the flux in the vadose zone towards shallow unconfined aquifers, Fg$$ {F}_g $$, in the Umbria region (central Italy). Then, according to the methodology proposed in Bongioannini Cerlini et al. (2021), where for the considered aquifers most of the recharge derives from the unsaturated zone, Fg$$ {F}_g $$ is used for simulating the water table evolution in time. With the aim of assessing which reanalysis is the most appropriate in simulating the evolution of groundwater levels, the properties of the correspondent land surface models (LSM) are examined, as they provide Fg$$ {F}_g $$. For the considered aquifers, the analysis of the performance of the selected reanalyses confirms the validity of the proposed approach. Moreover, it points out the crucial role of the spreading of the water table elevation with respect to its mean value, as a significant parameter for selecting the most adequate reanalysis to use. In addition, the role in the LSM of the explored soil depth, hydraulic conductivity curve, and spatial resolution is highlighted. These results, in line with recent literature on the performance of the reanalyses, suggest to extend future work to other regions of the world.

show abstract

Groundwater Level Forecast Via a Discrete Space-State Modelling Approach as a Surrogate to Complex Groundwater Simulation Modelling

Cited by 15 publications

References 44 publications

Dynamic Response Characteristics of Shallow Groundwater Level to Hydro-Meteorological Factors and Well Irrigation Water Withdrawals under Different Conditions of Groundwater Buried Depth

Dynamic Response Characteristics of Shallow Groundwater Level to Hydro-Meteorological Factors and Well Irrigation Water Withdrawals under Different Conditions of Groundwater Buried Depth

The contribution of remote sensing and input feature selection for groundwater level prediction using LSTM neural networks in the Oum Er-Rbia Basin, Morocco

Performance of three reanalyses in simulating the water table elevation in different shallow unconfined aquifers in Central Italy

Contact Info

Product

Resources

About