Mapping groundwater potential zones using relative frequency ratio, analytic hierarchy process and their hybrid models: case of Nzhelele-Makhado area in South Africa

Muavhi, Nndanduleni; Thamaga, Kgabo Humphrey; Mutoti, Mulalo Isaih

doi:10.1080/10106049.2021.1936212

Cited by 27 publications

(25 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The groundwater controlling factors which were considered include slope angle, geomorphology, geology, lineament density, drainage density, rainfall, LULC and elevation. In AHP model, the pairwise comparison analysis of relative importance of groundwater controlling factors is based on expert opinion and knowledge (Saranya and Saravanan 2020;Muavhi et al 2021;Sengani et al 2021). The reliability of this analysis is assessed through CR which is mathematical indicator of judgment concerning a decision made randomly (Saaty 1980).…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Using Geospatial Techniques and Analytic Hierarchy Process to Map Groundwater Potential Zones

Muavhi¹,

Mutoti

2022

Groundwater

View full text Add to dashboard Cite

This study is conducted in Luvuvhu River Catchment (LRC) of South Africa, which has numerous major agricultural farms that are located in the upper catchment, especially in Levubu Valley. The significant irrigation developments in upper catchment have resulted in a decrease in the yield of surface water resources to such an extent that these resources struggle to meet domestic and industrial demand. The aim of this study is to delineate groundwater potential zones (GWPZ) as a way of establishing alternative water resources to relieve the overly stressed surface water resources. Various datasets are processed to extract groundwater controlling factors. Map layers of controlling factors are assigned weights according to their relative importance to groundwater occurrence using analytic hierarchy process and then integrated based on weighted sum analysis to generate GWPZ map. Rainfall infiltration breakthrough (RIB) and area under curve (AUC) are used to validate the GWPZ map. GWPZ map shows that lower catchment has very high groundwater potential covering about 409 km2. Nonetheless, about 50% of LRC spatially falls within high groundwater potential zone. Groundwater recharge, based on RIB for three boreholes, that is, A9N0007, A9N0008, and A9N0018 around Levubu Valley is estimated at 8.3, 15.4, and 16.2%, respectively. Boreholes A9N0018 and A9N0018 correspond to moderate to high groundwater potential zone, whereas A9N007 coincides with low to moderate zone. Considering the groundwater recharge estimates and associated potential zones, RIB results correspond well with GWPZ map. Also, an AUC, based on 26 boreholes, of 70.9% is achieved; thus, indicating a reliable model.

show abstract

Section: Resultsmentioning

confidence: 99%

“…This declination calls for adequate implementation of groundwater management plans. Also, adequate identification of groundwater potential zone (GWPZ) can be of great assistance in the efficient implementation of groundwater management plans (Arivalagan et al 2014; Abuzied et al 2016; Muavhi et al 2021).…”

Section: Introductionmentioning

confidence: 99%

Using Geospatial Techniques and Analytic Hierarchy Process to Map Groundwater Potential Zones

Muavhi¹,

Mutoti

2022

Groundwater

View full text Add to dashboard Cite

show abstract

“…Therefore, the impact of these variables was evaluated (Table 1), and we eliminated the variables having less impact from modeling (Table 4). These less important variables could affect the prediction procedure (Maskooni et al 2020;Muavhi et al 2021). Also, we applied machine learning technique like random forest for computing the importance of the GWP conditioning variables to the GWP models (Fig.…”

Section: Discussionmentioning

confidence: 99%

“…The utilization of EML algorithms has been substantially increased for higher accuracy in GWP mapping (Al-Abadi and Shahid 2015). Ensemble modeling included two or more ML algorithms to enhance the prediction accuracy (Muavhi et al 2021;Pham et al 2021;Farzin et al 2021). Ensemble modeling can mitigate the flaws of an individual model (Talukdar et al 2020(Talukdar et al , 2021bRahmati et al 2016).…”

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

“…Díaz-Alcaide and Martínez-Santos (2019) carried out a review of GPM approaches, analyzing the definitions of GPM, the variables that are typically involved in GPM studies and the data integration procedures available in the literature. These authors found that most of the existing studies rely on expert-decision approaches like analytical hierarchy processes (Muavhi et al, 2021), weight-of-evidence approaches (Ahmed et al, 2021), fuzzy analytical hierarchy processes (Boughariou et al, 2021), multi-criteria decision-making Fig. 1.…”

Section: Introductionmentioning

confidence: 99%

Multiclass spatial predictions of borehole yield in southern Mali by means of machine learning classifiers

Gómez-Escalonilla

Diancoumba²,

Traoré³

et al. 2022

Journal of Hydrology: Regional Studies

View full text Add to dashboard Cite

Mapping groundwater potential zones using relative frequency ratio, analytic hierarchy process and their hybrid models: case of Nzhelele-Makhado area in South Africa

Cited by 27 publications

References 28 publications

Using Geospatial Techniques and Analytic Hierarchy Process to Map Groundwater Potential Zones

Using Geospatial Techniques and Analytic Hierarchy Process to Map Groundwater Potential Zones

Novel hybrid models to enhance the efficiency of groundwater potentiality model

Multiclass spatial predictions of borehole yield in southern Mali by means of machine learning classifiers

Contact Info

Product

Resources

About