Self-Learning Random Forests Model for Mapping Groundwater Yield in Data-Scarce Areas

Sameen, MI; Pradhan, B; Lee, S

Self-Learning Random Forests Model for Mapping Groundwater Yield in Data-Scarce Areas

Sameen, MI Pradhan, B

Lee, S

Permalink

Publication Type:: Journal Article
Citation:: Natural Resources Research, 2019, 28 (3), pp. 757 - 775
Issue Date:: 2019-07-01

Closed Access

	Filename	Description	Size
	Sameen2018_Article_Self-LearningRandomForestsMode.pdf	Accepted Manuscript Version	14.46 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Sameen, MI	en_US
dc.contributor.author	Pradhan, B https://orcid.org/0000-0001-9863-2054	en_US
dc.contributor.author	Lee, S	en_US
dc.date.issued	2019-07-01	en_US
dc.identifier.citation	Natural Resources Research, 2019, 28 (3), pp. 757 - 775	en_US
dc.identifier.issn	1520-7439	en_US
dc.identifier.uri	http://hdl.handle.net/10453/130837
dc.description.abstract	© 2018, International Association for Mathematical Geosciences. Globally, groundwater plays a major role in supplying drinking water for urban and rural population and is used for irrigation to grow crops and in many industrial processes. A novel self-learning random forest (SLRF) model is developed and validated for groundwater yield zonation within the Yeondong Province in South Korea. This study was conducted with an inventory data initially divided randomly into 70% for training and 30% for testing and 13 groundwater-conditioning factors. SLRF was optimized using Bayesian optimization method. We also compared our method to other machine learning methods including support vector machine (SVM), artificial neural networks (ANN), decision trees (DT), and voting ensemble models. Model validation was accomplished using several methods, including a confusion matrix, receiver operating characteristics, cross-validation, and McNemar’s test. Our proposed self-learning method improves random forest (RF) generalization performance by about 23%, with SLRF success rates of 0.76 and prediction rates of 0.83. In addition, the optimized SLRF performed better [according to a threefold cross-validated AUC (area under curve) of 0.75] than that using randomly initialized parameters (0.57). SLRF outperformed all of the other models for the testing dataset (RF, SVM, ANN, DT, and Voted ANN-RF) when the overall accuracy, prediction rate, and cross-validated AUC metrics were considered. The SLRF also estimated the contribution of individual groundwater conditioning factors and showed that the three most influential factors were geology (1.00), profile curvature (0.97), and TWI (0.95). Overall, SLRF effectively modeled groundwater potential, even within data-scarce regions.	en_US
dc.relation.ispartof	Natural Resources Research	en_US
dc.relation.isbasedon	10.1007/s11053-018-9416-1	en_US
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Geochemistry & Geophysics	en_US
dc.title	Self-Learning Random Forests Model for Mapping Groundwater Yield in Data-Scarce Areas	en_US
dc.type	Journal Article
utslib.citation.volume	3	en_US
utslib.citation.volume	28	en_US
utslib.for	0406 Physical Geography and Environmental Geoscience	en_US
utslib.for	0502 Environmental Science and Management	en_US
utslib.for	0914 Resources Engineering and Extractive Metallurgy	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Information, Systems and Modelling
pubs.organisational-group	/University of Technology Sydney/Strength - CAMGIS - Centre for Advanced Modelling and Geospatial lnformation Systems
utslib.copyright.status	closed_access	*
pubs.issue	3	en_US
pubs.publication-status	Published	en_US
pubs.volume	28	en_US

Abstract:

© 2018, International Association for Mathematical Geosciences. Globally, groundwater plays a major role in supplying drinking water for urban and rural population and is used for irrigation to grow crops and in many industrial processes. A novel self-learning random forest (SLRF) model is developed and validated for groundwater yield zonation within the Yeondong Province in South Korea. This study was conducted with an inventory data initially divided randomly into 70% for training and 30% for testing and 13 groundwater-conditioning factors. SLRF was optimized using Bayesian optimization method. We also compared our method to other machine learning methods including support vector machine (SVM), artificial neural networks (ANN), decision trees (DT), and voting ensemble models. Model validation was accomplished using several methods, including a confusion matrix, receiver operating characteristics, cross-validation, and McNemar’s test. Our proposed self-learning method improves random forest (RF) generalization performance by about 23%, with SLRF success rates of 0.76 and prediction rates of 0.83. In addition, the optimized SLRF performed better [according to a threefold cross-validated AUC (area under curve) of 0.75] than that using randomly initialized parameters (0.57). SLRF outperformed all of the other models for the testing dataset (RF, SVM, ANN, DT, and Voted ANN-RF) when the overall accuracy, prediction rate, and cross-validated AUC metrics were considered. The SLRF also estimated the contribution of individual groundwater conditioning factors and showed that the three most influential factors were geology (1.00), profile curvature (0.97), and TWI (0.95). Overall, SLRF effectively modeled groundwater potential, even within data-scarce regions.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/130837