Application of GIS-based data driven random forest and maximum entropy models for groundwater potential mapping: A case study at Mehran Region, Iran

Rahmati, Omid; Pourghasemi, Hamid Reza; Melesse, Assefa M.

doi:10.1016/j.catena.2015.10.010

Cited by 479 publications

(221 citation statements)

References 81 publications

Supporting

Mentioning

211

Contrasting

Unclassified

Order By: Relevance

“…Several statistical methods can also be adopted for groundwater mapping where adequate information on different influencing parameters to groundwater accumulation and movement are available. These include frequency ratio (Davoodi et al 2013), multi-criteria decision evaluation (Murthy and Mamo 2009;Kumar et al 2014), logistic regression model (Ozdemir 2011), weights-of-evidence model (Ozdemir 2011;Pourtaghi and Pourghasemi 2014), random forest model (Rahmati et al 2016Naghibi et al 2016, maximum entropy model (Rahmati et al 2016), boosted regression tree (Naghibi et al 2016;Naghibi and Pourghasemi 2015), classification and regression tree (Naghibi et al 2016), multivariate adaptive regression spline model (Zabihi et al 2016), certainty factor model (Zabihi et al 2016), evidential belief function (Pourghasemi and Beheshtirad 2015;Naghibi and Pourghasemi 2015), and generalized linear model (Naghibi and Pourghasemi 2015). These information are lacking in many third world country hence proper understanding of hydrogeological characteristics for successful exploitation of groundwater in basement areas depend largely on geophysical methods.…”

Section: Introductionmentioning

confidence: 99%

Geophysical evaluation of groundwater potential in part of southwestern Basement Complex terrain of Nigeria

et al. 2017

View full text Add to dashboard Cite

The geophysical assessment of groundwater in Awa-Ilaporu, near Ago Iwoye southwestern Nigeria was carried out with the aim of delineating probable areas of high groundwater potential. The area falls within the Crystalline Basement Complex of southwestern Nigeria which is predominantly underlain by banded gneiss, granite gneiss and pegmatite. The geophysical investigation involves the very low frequency electromagnetic (VLF-EM) and Vertical Electrical Sounding (VES) methods. The VLF-EM survey was at 10 m interval along eight traverses ranging between 290 and 700 m in length using ABEM WADI VLF-EM unit. The VLF-EM survey was used to delineate areas with conductive/fractured zones. Twenty-three VES surveys were carried out with the use of Campus Ohmega resistivity meter at different location and at locations areas delineated as high conductive areas by VLF-EM survey. The result of VLF-EM survey along its traverse was used in delineating high conductive/fractured zones, it is, however, in agreement with the delineation of the VES survey. The VES results showed 3-4 geoelectric layers inferred as sandy topsoil, sandy clay, clayey and fractured/fresh basement. The combination of these two methods, therefore, helped in resolving the prospecting location for the groundwater yield in the study area.

show abstract

Section: Introductionmentioning

confidence: 99%

Geophysical evaluation of groundwater potential in part of southwestern Basement Complex terrain of Nigeria

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Geospatial information has proven useful to explore the link between water and poverty [18,19]. In the case of groundwater resources, GIS has frequently been applied to delineate groundwater potential areas [20][21][22][23][24], study the spatial distribution of aquifer recharge [25][26][27], or assess the vulnerability of aquifer systems to pollution [28][29][30].…”

Section: Methodological Precedents Research Objectives and Noveltiesmentioning

confidence: 99%

Mapping the Viability, Time, and Cost of Manual Borehole Drilling in Developing Regions

Martínez‐Santos

Martín-Loeches

Solera

et al. 2017

Water

View full text Add to dashboard Cite

While access to water remains an issue in arid and semiarid regions across the world, aquifers have the potential to help millions of people out of poverty by providing a reliable source of drinking and irrigation water. Manual boreholes are increasingly advocated as a safe and cost-effective substitute to mechanized drilling, as well as to traditional excavation methods. This research banks on the assumption that field and remote sensing data can be integrated within a geospatial database in order to map the viability of manual boreholes based on factors such as rock type, water table depth, landforms, or water quality. The approach presents three main novelties in relation to methodological precedents: (1) outcomes are not only expressed in terms of technical feasibility, but also as a function of drilling time and cost; (2) maps refer to a specific drilling technique; and (3) results take into account borehole diameter, as this constrains both drilling time and cost. The method provides univocal outcomes that can be immediately useful for non-experts, donors, planners, or practitioners and that can be readily exported to other catchment-scale settings. Results were validated against geophysical data.

show abstract

“…This provides maximum entropy while avoiding assumptions on the unknown, hence the name of the classifier. MaxEnt was proposed to estimate geographic species distribution and potential habitat [56], to classify vegetation from remote sensing images [65], and groundwater potential mapping [66]. In our study, MaxEnt was applied with default parameter values in GEE as follows: weight for L1 regularization set to 0, weight for L2 regularization set to 0.00001, epsilon set to 0.00001, minimum number of iterations set to 0, and maximum number of iterations set to 100.…”

Section: Vegetation Index (Vi) Formulamentioning

confidence: 99%

A Cloud-Based Multi-Temporal Ensemble Classifier to Map Smallholder Farming Systems

et al. 2018

View full text Add to dashboard Cite

Smallholder farmers cultivate more than 80% of the cropland area available in Africa. The intrinsic characteristics of such farms include complex crop-planting patterns, and small fields that are vaguely delineated. These characteristics pose challenges to mapping crops and fields from space. In this study, we evaluate the use of a cloud-based multi-temporal ensemble classifier to map smallholder farming systems in a case study for southern Mali. The ensemble combines a selection of spatial and spectral features derived from multi-spectral Worldview-2 images, field data, and five machine learning classifiers to produce a map of the most prevalent crops in our study area. Different ensemble sizes were evaluated using two combination rules, namely majority voting and weighted majority voting. Both strategies outperform any of the tested single classifiers. The ensemble based on the weighted majority voting strategy obtained the higher overall accuracy (75.9%). This means an accuracy improvement of 4.65% in comparison with the average overall accuracy of the best individual classifier tested in this study. The maximum ensemble accuracy is reached with 75 classifiers in the ensemble. This indicates that the addition of more classifiers does not help to continuously improve classification results. Our results demonstrate the potential of ensemble classifiers to map crops grown by West African smallholders. The use of ensembles demands high computational capability, but the increasing availability of cloud computing solutions allows their efficient implementation and even opens the door to the data processing needs of local organizations.

show abstract

Application of GIS-based data driven random forest and maximum entropy models for groundwater potential mapping: A case study at Mehran Region, Iran

Cited by 479 publications

References 81 publications

Geophysical evaluation of groundwater potential in part of southwestern Basement Complex terrain of Nigeria

Geophysical evaluation of groundwater potential in part of southwestern Basement Complex terrain of Nigeria

Mapping the Viability, Time, and Cost of Manual Borehole Drilling in Developing Regions

A Cloud-Based Multi-Temporal Ensemble Classifier to Map Smallholder Farming Systems

Contact Info

Product

Resources

About