Delineation of groundwater potential zones by means of ensemble tree supervised classification methods in the Eastern Lake Chad basin

Gómez-Escalonilla, Víctor; Vogt, Marie-Louise; Elisa, Destro; Isseini, Moussa; Origgi, Giaime; Daïra, Djoret; Martínez‐Santos, Pedro; Holecz, F.

doi:10.1080/10106049.2021.2007298

Cited by 11 publications

(6 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset is however imbalanced in terms of yield levels: 36 points (7.4%) were classified as negative, 323 points (66.9%) present borehole yields of between 0.5 and 5 m 3 /h, and 124 points (25.4%) exceed 5 m 3 /h. In the experience of the authors, this is common in regional borehole databases (Gómez-Escalonilla et al, 2021), and is likely attributable to the fact that negative boreholes are reported to the authorities less frequently than positive boreholes. Because data imbalances cause difficulties to the predictive potential of the algorithms, a series of trial runs were carried out to determine the optimal threshold between borehole yield classes.…”

Section: Target Variablementioning

confidence: 92%

“…In reference to the last element, ML models, the MLMapper 2.0 code (Gómez-Escalonilla et al, 2021, 2022 has been used in this research to develop spatial predictions of borehole yield. The code is an evolution of the original MLMapper tool developed by Martinez- Santos and Renard (2020).…”

Section: Machine Learning Modelsmentioning

confidence: 99%

“…This led to choosing Extra Trees (ETC), Logistic Regression (LRG) and the Gradient Boosting Classifier (GBC) as the most suitable. More information on discarded algorithms can be found in previous studies (Gómez-Escalonilla et al, 2021, 2022Martínez-Santos and Renard, 2020;Pedregosa et al, 2011).…”

Section: Machine Learning Modelsmentioning

confidence: 99%

“…From a geographical standpoint, ML-GPM studies have been carried out mainly in Asia, while there are very few in the African continent (Braham et al, 2022;Gómez-Escalonilla et al, 2021, 2022Martínez-Santos and Renard, 2020;Namous et al, 2021). Moreover, ours is one of the first studies in the literature addressing groundwater potential based on a multiclass approach.…”

Section: Introductionmentioning

confidence: 98%

“…The recent literature showcases several examples of ML algorithms in groundwater potential mapping studies. These include support vector machines (Al-Fugara et al, 2022;Panahi et al, 2020), decision trees (Al-Abadi et al, 2021;Arabameri et al, 2021;Braham et al, 2022), artificial neural networks (Chen et al, 2021;Nguyen et al, 2020;Hakim et al, 2022), and ensemble methods like boosting, random forests and extra trees classification, among others (Bai et al, 2022;Choudhary et al, 2022;Gómez-Escalonilla et al, 2021, 2022Martinsen et al, 2022;Sachdeva and Kumar, 2021).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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

Section: Target Variablementioning

confidence: 92%

Section: Machine Learning Modelsmentioning

confidence: 99%

Section: Machine Learning Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

La integración de datos geológicos, hidrogeológicos y geofísicos con el fin de identificar los recursos de aguas subterráneas en zonas de basamento granítico (Macizo de Guéra, Chad)

Nouradine,

Schamper,

Valdes

et al. 2024

Hydrogeol J

View full text Add to dashboard Cite

In Chad, hard-rock aquifers are the main source of drinking water for the population located on basement areas. In these basement aquifers, and in particular those of the Guéra region, water drilling failure rates remain high despite research on one- and two-dimensional electrical resistivity techniques and lineaments as a means to improve access to the resource, mainly because these techniques are only used on an observational and structural basis to locate fractures. This study combines electrical resistivity tomography (ERT) with geology, hydrogeology and geomorphology, in order to characterise the structure and geometry of the aquifer system, assess borehole productivity and determine the factors controlling it. After validating the large dataset and its representativeness, 315 high- and low-yield wells, of which 41 have complete geophysical datasets, were selected. This large dataset allows a multi-parameter approach to (1) better characterise each facies according to its electrical resistivity and (2) clearly identify the main formations constituting the local conceptual hydrogeological model. The most suitable areas for productive boreholes are characterised by the presence of an overburden of <20 m depth, well-developed weathered and fractured horizons of granites and biotite granites (preferably) containing little or no clay, and a nearby drainage network. The most substantial flow rates are found in the first 30 m of the fissured horizon, below the base of the alterites. The experience gained from the present study will guide future analysis of ERT sections in order to reduce the probability of drilling dry wells.

show abstract

Proxy modeling approach to evaluate groundwater recharge potentiality zones in the data scarce area of upper Blue Nile Basin, Ethiopia

Tegegne

Lohani

Eshete

2023

Environ Monit Assess

View full text Add to dashboard Cite

Delineation of groundwater potential zones by means of ensemble tree supervised classification methods in the Eastern Lake Chad basin

Cited by 11 publications

References 51 publications

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

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

La integración de datos geológicos, hidrogeológicos y geofísicos con el fin de identificar los recursos de aguas subterráneas en zonas de basamento granítico (Macizo de Guéra, Chad)

Proxy modeling approach to evaluate groundwater recharge potentiality zones in the data scarce area of upper Blue Nile Basin, Ethiopia

Contact Info

Product

Resources

About