Forecasting groundwater anomaly in the future using satellite information and machine learning

Soltani, Keyvan; Azari, Arash

doi:10.1016/j.jhydrol.2022.128052

Cited by 15 publications

(10 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MK-based estimated trend results are given in Table 2. The results demonstrate a decreasing trend for the TWS and GWS over In another study, the total GWS loss of the basin from 2002 to 2020 was estimated to be about À7:34 km 3 (Soltani & Azari, 2022), which is comparable to our findings.…”

Section: Trend Analysis Resultssupporting

confidence: 90%

“…According to the Taylor diagram, the correlation between the STL-based TWS and CLSM-TWS is 0.88, 0.89 and 0.91 for the JPL, GSFC and CSR data, respectively. The good performance of the proposed STL-based gapfilling approach is also verified by comparing it to the findings of previous studies Soltani and Azari (2022). applied the Group method of data Handling (GMDH) machine learning technique to model TWS values over the LUB.…”

supporting

confidence: 57%

“…The good performance of the proposed STL‐based gap‐filling approach is also verified by comparing it to the findings of previous studies. Soltani and Azari (2022) applied the Group method of data Handling (GMDH) machine learning technique to model TWS values over the LUB. According to Soltani and Azari (2022), the GMDH was considered a successful GRACE gap‐filling technique that yields very good results in simulating the missing TWS values over the LUB with the best correlation of 0.73.…”

Section: Resultsmentioning

confidence: 99%

“…applied the Group method of data Handling (GMDH) machine learning technique to model TWS values over the LUB. According toSoltani and Azari (2022), the GMDH was considered a successful GRACE gap-filling technique that yields very good results in simulating the missing TWS values over the LUB with the best correlation of 0.73.3.5 | Variations of TWSTemporal variations of TWS over the LUB were drawn based on the basin-average TWS on the monthly scale (Figure3). The variations of TWS over the LUB reveal that there is a high level of agreement between different GRACE solutions and the CLSM-TWS.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Model‐coupled GRACE‐based analysis of hydrological dynamics of drying Lake Urmia and its basin

Khorrami

Ali

Sahin

et al. 2023

Hydrological Processes

View full text Add to dashboard Cite

Lake Urmia basin (LUB), in northwestern Iran, is under the influence of extreme degradation due to a number of natural and anthropogenic factors. The existence of the Lake is critical for the microclimate of the region as well as the quality of human life and wildlife, which necessitates an up-to-date and holistic analysis of its hydrological dynamics. In this premise, satellite-based terrestrial water storage (TWS) received from the Gravity Recovery and Climate Experiment (GRACE) mission was coupled with hydrometeorological modelling and assessment tools to analyse the hydrological status of the lake and its basin. As a new gap-filling approach, the Seasonal-Trend decomposition using Locally estimated scatterplot smoothing (LOESS) (STL) decomposition technique was proposed in this study to reconstruct the missing TWS data.Integrating satellite precipitation data with the Catchment Land Surface Model (CLSM) and WaterGAP model outputs, the hydrological status of the lake was investigated. The STL-based TWS turned out to concord well with the simulated TWS from the CLSM indicating the acceptable performance of the proposed technique.The findings revealed that the LUB had undergone an alarming hydrological situation from 2003 to 2021 with a total loss of 10 and 7:56 km 3 from its TWS and groundwater storage (GWS), respectively. The water level time series also indicated that the water level of the lake had diminished with an annual rate of À70 AE 21 cm=year corresponding to a total water level depletion of about 13:35 AE 3:9 m during the 2003-2021 period. The GRACE-derived TWS and GWS also agreed well with the CLSM simulations. Assessment of the extreme events of the LUB suggested that the basin suffered from a severe dry event in 2008 resulting in the depletion of its water storage and water level. It was also found that from 2003 onward, a critical hydrological setting had dominated the LUB with a negative hydrological balance of À0:96 km 3 .

show abstract

Section: Trend Analysis Resultssupporting

confidence: 90%

supporting

confidence: 57%

Section: Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Model‐coupled GRACE‐based analysis of hydrological dynamics of drying Lake Urmia and its basin

Khorrami

Ali

Sahin

et al. 2023

Hydrological Processes

View full text Add to dashboard Cite

show abstract

“…MAE is the average of absolute differences between predicted and observed values and is indifferent to the direction of errors. The model will have the best prediction if the values of RMSE and MAE are close to zero 29 . The correlation coefficient measures the degree of similarity between predicted and measured data.…”

Section: Methodsmentioning

confidence: 99%

Application of classical and novel integrated machine learning models to predict sediment discharge during free-flow flushing

Javadi

Qaderi

Ahmadi

et al. 2022

Sci Rep

View full text Add to dashboard Cite

In this study, the capabilities of classical and novel integrated machine learning models were investigated to predict sediment discharge (Qs) in free-flow flushing. Developed models include Multivariate Linear Regression (MLR), Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), Group Method of Data Handling (GMDH), and four hybrid forms of GMDH and Support Vector Regression (SVR) in combination with Henry Gas Solubility Optimization (HGSO) and Equilibrium Optimizer (EO) algorithms. The number of 160 datasets that were applied to assess these models was extracted from the Janssen (PhD’s Thesis, Engineering, Civil and Environmental Engineering. University of California, 1999) experimental study. Input parameters to predict Qs included the water level in the reservoir (hw), bed level in the flushing channel (hb), outflow (Qout), inflow (Qin), and elapsed time of flushing (T). The performance of all models was evaluated by four statistical indices of root mean square error (RMSE), mean absolute error (MAE), correlation coefficient (R2), and Mean absolute relative error (MARE). Evaluation of results demonstrated that the HGSO and EO algorithms could enhance the accuracy of the GMDH model (up to 26% and 22% in terms of RMSE), respectively. According to statistical criteria, the SVR-EO and SVR-HGSO provided the highest accuracy in both training (R2 = 0.98) and validation phases (R2 = 0.96). Moreover, among the developed models, the GMDH-HGSO algorithm provided excellent fitness to the observed data (R2 = 0.96, RMSE = 22.37, MAE = 15.65, and MARE = 0.26). The results indicated the high efficiency of the HGSO and EO algorithms in improving the accuracy of the GMDH and SVR models. However, among the developed models, the GMDH-HGSO is the most accurate model and is recommended for sediment transport modelling.

show abstract

Terrestrial water storage anomaly estimating using machine learning techniques and satellite‐based data (a case study of Lake Urmia Basin)

Soltani,

Azari

2023

Irrigation and Drainage

Self Cite

View full text Add to dashboard Cite

In this study, the Terrestrial Water Storage Anomaly (TWSA) in the Lake Urmia Basin (LUB) was obtained by using the GRACE satellites. The whole study area was covered by 10 GRACE/GFO pixels, and the TWSA value was calculated for these 10 pixels. Examining the changing trend showed that the value of TWSA in the LUB has a decreasing trend and fluctuates from approximately −200 to +200 compared to the average value. The TWSA was modelled using the group method of data handling (GMDH) by considering six different parameters obtained from the European Centre for Medium‐Range Weather Forecasts (ECMWF) Reanalysis V5 (ERA5) and the Global Land Data Assimilation System version 2.0 (GLDAS V2.0). Finally, the best models with two to six input variables were selected. Among the models with different inputs, the GMDH Model 2, with three inputs, had the best performance compared to the other models. After choosing the best inputs in calculating the TWSA value by the GMDH, the TWSA value was also modelled by using the Adaptive Neuro‐Fuzzy Inference System (ANFIS), the Extreme Learning Machine (ELM) and the Artificial Neural Network (ANN). The results showed that GMDH not only outperformed other models but also provided some simple equations to apply in practical tasks.

show abstract

Forecasting groundwater anomaly in the future using satellite information and machine learning

Cited by 15 publications

References 60 publications

Model‐coupled GRACE‐based analysis of hydrological dynamics of drying Lake Urmia and its basin

Model‐coupled GRACE‐based analysis of hydrological dynamics of drying Lake Urmia and its basin

Application of classical and novel integrated machine learning models to predict sediment discharge during free-flow flushing

Terrestrial water storage anomaly estimating using machine learning techniques and satellite‐based data (a case study of Lake Urmia Basin)

Contact Info

Product

Resources

About