Comparing four machine learning model performances in forecasting the alluvial aquifer level in a semi-arid region

Bilali, Ali El; Taleb, Abdeslam; Brouziyne, Youssef

doi:10.1016/j.jafrearsci.2021.104244

Cited by 25 publications

(9 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…kNN and SVM models had a lower performance for simulating the SSL in all studied stations. This is in agreement with previous published studies, such as Wang et al [49] and El Bilali et al [14], where their findings demonstrated that the tree-based and ANN models are more accurate than SVM and k-NN ones. Regarding the SSL prediction, ref.…”

Section: Discussionsupporting

confidence: 93%

“…Indeed, their construction relies on the statistical input-output equation rather than explaining the mechanism involved in the process. Recently, several studies showed that the data-based models are powerful tools to overcome some limitations of the conceptual-based models in predicting the water resources status [14][15][16][17][18]. For instance, ref.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Daily Suspended Sediment Load Using Machine Learning and NARX Hydro-Climatic Inputs in Semi-Arid Environment

Ezzaouini

Mahé

Kacimi

et al. 2022

Water

Self Cite

View full text Add to dashboard Cite

Sediment transport in basins disturbs the ecological systems of the water bodies and leads to reservoir siltation. Its evaluation is crucial for managing water resources. The practical application of the process-based model can confront some limitations noticed in the lower accuracy during the validation process due to the lack of reliable physical datasets. In this study, we attempt to apply machine-learning-based modeling (ML) to predict the suspended sediment load, using hydro-climatic data as input variables in the semi-arid Bouregreg basin, Morocco. To that end, data for the years 2016 to 2020 were used for the training process, and the validation was performed with 2021 data. The results showed that most ML models have good accuracy, with a Nash–Schiff efficiency (NSE) ranging from 0.47 to 0.80 during the validation phase, which indicates satisfactory performances in predicting the SSL. Furthermore, the models were ranked against their generalization ability (GA), which revealed that the developed models are good to excellent in terms of GA. Overall, the present study provides new insight into predicting the SSL in a semi-arid environment, such as the Bouregreg basin.

show abstract

Section: Discussionsupporting

confidence: 93%

Section: Introductionmentioning

confidence: 99%

Predicting Daily Suspended Sediment Load Using Machine Learning and NARX Hydro-Climatic Inputs in Semi-Arid Environment

Ezzaouini

Mahé

Kacimi

et al. 2022

Water

Self Cite

View full text Add to dashboard Cite

show abstract

“…The traditional hydrogeochemical software such as MINTEQA2, WATEQ, Netpath, EQ3/6 and PHREEQC/QE are constantly upgraded (Zhang and Zhang, 2019), and the functions of groundwater flow numerical simulation software such as GMS, MODFLOW and FEFLOW are more and more perfect (Li et al, 2021;Liu et al, 2022a). Neural network learning, deep learning and machine learning based on big data have been widely applied to solve the problem of highdimensional uncertain GCE (Mo, 2019;El Bilali et al, 2021). For example, explored the low-temperature hydrogeological process of frozen soil environment through three-dimensional numerical simulation (Liu et al, 2022b).…”

Section: New Methods Of Groundwater Chemical Evolutionmentioning

confidence: 99%

Theoretical progress of groundwater chemical evolution based on Tóthian theory: A review

Dong

Gao²

2022

Front. Mar. Sci.

View full text Add to dashboard Cite

Tóthian theory refers to the gravity driven groundwater flow system (GFS) theory represented by Tóth, which mainly expounds the driving and distribution law of groundwater. The establishment and development of this theory not only deepened people’s understanding of the driving and distribution law of groundwater, but also greatly promoted the study of groundwater chemical evolution (GCE). Modern GCE research is mostly based on Tóthian theory, characterized by combining with advanced scientific and technological means. Based on the clue of time, this paper is divided into two parts. The first part mainly summarizes the establishment and development of Tóthian theory, including the exploration of groundwater driving force and distribution form by hydrogeologists before Tóthian theory, and the enrichment, development and application of Tóthian theory by geologists after its establishment. The second part mainly combs the main theories and application progress of GCE mechanism research, including the main theories and findings of GCE research before the emergence of Tóthian theory, as well as the research progresses of GCE after the emergence of Tóthian theory. With the flow of groundwater in GFS, groundwater undergoes continuous chemical evolution, which eventually leads to the transformation of hydrochemical types and the gradual increase of total dissolved solids (TDS). The distribution of GFS and GCE complement each other. The distribution of GFS directly determines the model of GCE, and the results of GCE also play a certain role in the distribution of GFS. GCE mainly includes dissolution, precipitation, cation exchange and adsorption, which is affected by the physical and chemical conditions of permeable media, organic matter content and microorganisms. GCE has the characteristics of universality, sustainability and diversity. With the increasing global population and the progresses of science and technology, the impact of human life, industrial and agricultural production on groundwater is deepening. The aggravation of pollution directly changes the chemical compositions of groundwater, resulting in changes of the law of GCE.

show abstract

“…( 2) Techniques for multicriteria decision analysis (MCDA), such as the analytic hierarchy process (AHP) (Kumar et al 2020;Murmu et al 2019) and TOPSIS (Mandal et al 2021;Zaree et al 2019). Experts' judgment has tuned semiquantitative models (AHP), but for comparable geo-environmental elements or locations, the models need extensive understanding of groundwater and conditioning variables, which is seldom accessible (El Bilali et al 2021;Mogaji et al 2016). Statistical approaches have been widely regarded as the best way for GWP mapping at sizes of 1:20,000 to 1:50,000, as they can map springs and wells in detail (Mallick et al 2021a;Arshad et al 2020).…”

Section: Introductionmentioning

confidence: 99%

Novel hybrid models to enhance the efficiency of groundwater potentiality model

et al. 2022

View full text Add to dashboard Cite

The present study aimed to create novel hybrid models to produce groundwater potentiality models (GWP) in the Teesta River basin of Bangladesh. Six ensemble machine learning (EML) algorithms, such as random forest (RF), random subspace, dagging, bagging, naïve Bayes tree (NBT), and stacking, coupled with fuzzy logic (FL) models and a ROC-based weighting approach have been used for creating hybrid models integrated GWP. The GWP was then verified using both parametric and nonparametric receiver operating characteristic curves (ROC), such as the empirical ROC (eROC) and the binormal ROC curve (bROC). We conducted an RF-based sensitivity analysis to compute the relevancy of the conditioning variables for GWP modeling. The very high and high groundwater potential regions were predicted as 831–1200 km2 and 521–680 km2 areas based on six EML models. Based on the area under the curve of the ROC, the NBT (eROC: 0.892; bROC: 0.928) model outperforms rest of the models. Six GPMs were considered variables for the next step and turned into crisp fuzzy layers using the fuzzy membership function, and the ROC-based weighting approach. Subsequently four fuzzy logic operators were used to assimilate the crisp fuzzy layers, including AND, OR, GAMMA0.8, and GAMMA 0.9, as well as GAMMA0.9. Thus, we created four hybrid models using FL model. The results of the eROC and bROC curve showed that GAMMA 0.9 operator outperformed other fuzzy operators-based GPMs in terms of accuracy. According to the validation outcomes, four hybrid models outperformed six EML models in terms of performance. The present study will aid in enhancing the efficiency of GPMs in preparing viable planning for groundwater management.

show abstract

Comparing four machine learning model performances in forecasting the alluvial aquifer level in a semi-arid region

Cited by 25 publications

References 64 publications

Predicting Daily Suspended Sediment Load Using Machine Learning and NARX Hydro-Climatic Inputs in Semi-Arid Environment

Predicting Daily Suspended Sediment Load Using Machine Learning and NARX Hydro-Climatic Inputs in Semi-Arid Environment

Theoretical progress of groundwater chemical evolution based on Tóthian theory: A review

Novel hybrid models to enhance the efficiency of groundwater potentiality model

Contact Info

Product

Resources

About