Developing groundwater potentiality models by coupling ensemble machine learning algorithms and statistical techniques for sustainable groundwater management
- 19 October 2021
- journal article
- research article
- Published by Taylor & Francis in Geocarto International
- Vol. 37 (25) , 7927-7953
Abstract
The present study intends to construct a logistic regression based hybrid EML model by considering nine standalone and ensemble machine learning (EML) algorithms as parameters for groundwater potentiality mapping (GPM) in the Teesta River basin of Bangladesh, including random forest (RF), M5P, artificial neural network (ANN), random subspace (RS), dagging, bagging, random tree, support vector machine (SVM), and REPTree. The GPM were then validated using the receiver operating characteristics (ROC) curve. To investigate the effect of the parameters for GPM, we used classification and regression tree (CART) and RF based sensitivity analysis. The very high (831-1200km2) and high groundwater potential areas (521-680km2), were predicted using nine EML algorithms and one hybrid model. The REPTree (AUC-0.893) model outperformed other nine models based on ROC's area under curve (AUC). Furthermore, the LR algorithm-based hybrid EML model outperformed the REPTree model in terms of precision (AUC: 0.933).Keywords
Funding Information
- Deanship of Scientific Research at King Khalid University
This publication has 123 references indexed in Scilit:
- Landslide hazard mapping using GIS and weight of evidence model in Qingshui River watershed of 2008 Wenchuan earthquake struck regionJournal of Earth Science, 2012
- Combining bagging, boosting, rotation forest and random subspace methodsArtificial Intelligence Review, 2010
- Cell type of origin influences the molecular and functional properties of mouse induced pluripotent stem cellsNature Biotechnology, 2010
- Delineation of landslide hazard areas on Penang Island, Malaysia, by using frequency ratio, logistic regression, and artificial neural network modelsEnvironmental Earth Sciences, 2009
- A comparative study of conventional, ANN black box, fuzzy and combined neural and fuzzy weighting procedures for landslide susceptibility zonation in Darjeeling HimalayasEngineering Geology, 2006
- Probabilistic landslide susceptibility mapping in the Lai Chau province of Vietnam: focus on the relationship between tectonic fractures and landslidesEnvironmental Geology, 2005
- The application of GIS-based logistic regression for landslide susceptibility mapping in the Kakuda-Yahiko Mountains, Central JapanGeomorphology, 2005
- Inhomogeneous continuum random trees and the entrance boundary of the additive coalescentProbability Theory and Related Fields, 2000
- The random subspace method for constructing decision forestsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Maximum attainable discrimination and the utilization of radiologic examinationsJournal of Chronic Diseases, 1982