Mapping groundwater contamination risk of multiple aquifers using multi-model ensemble of machine learning algorithms

Rahim Barzegar; Asghar Asghari Moghaddam; Ravinesh Deo; Elham Fijani; Evangelos Tziritis

doi:10.1016/j.scitotenv.2017.11.185

Mapping groundwater contamination risk of multiple aquifers using multi-model ensemble of machine learning algorithms

Sci Total Environ. 2018 Apr 15:621:697-712. doi: 10.1016/j.scitotenv.2017.11.185. Epub 2017 Nov 30.

Authors

Rahim Barzegar¹, Asghar Asghari Moghaddam², Ravinesh Deo³, Elham Fijani⁴, Evangelos Tziritis⁵

Affiliations

¹ Department of Earth Sciences, Faculty of Natural Sciences, University of Tabriz, Tabriz, Iran. Electronic address: rm.barzegar@tabrizu.ac.ir.com.
² Department of Earth Sciences, Faculty of Natural Sciences, University of Tabriz, Tabriz, Iran.
³ School of Agricultural Computational and Environmental Sciences, Institute of Agriculture and Environment (IAg&E), University of Southern Queensland, Springfield, Australia.
⁴ School of Geology, College of Science, University of Tehran, Tehran, Iran.
⁵ Hellenic Agricultural Organization, Soil and Water Resources Institute, 57400 Sindos, Greece.

PMID: 29197289
DOI: 10.1016/j.scitotenv.2017.11.185

Abstract

Constructing accurate and reliable groundwater risk maps provide scientifically prudent and strategic measures for the protection and management of groundwater. The objectives of this paper are to design and validate machine learning based-risk maps using ensemble-based modelling with an integrative approach. We employ the extreme learning machines (ELM), multivariate regression splines (MARS), M5 Tree and support vector regression (SVR) applied in multiple aquifer systems (e.g. unconfined, semi-confined and confined) in the Marand plain, North West Iran, to encapsulate the merits of individual learning algorithms in a final committee-based ANN model. The DRASTIC Vulnerability Index (VI) ranged from 56.7 to 128.1, categorized with no risk, low and moderate vulnerability thresholds. The correlation coefficient (r) and Willmott's Index (d) between NO₃ concentrations and VI were 0.64 and 0.314, respectively. To introduce improvements in the original DRASTIC method, the vulnerability indices were adjusted by NO₃ concentrations, termed as the groundwater contamination risk (GCR). Seven DRASTIC parameters utilized as the model inputs and GCR values utilized as the outputs of individual machine learning models were served in the fully optimized committee-based ANN-predictive model. The correlation indicators demonstrated that the ELM and SVR models outperformed the MARS and M5 Tree models, by virtue of a larger d and r value. Subsequently, the r and d metrics for the ANN-committee based multi-model in the testing phase were 0.8889 and 0.7913, respectively; revealing the superiority of the integrated (or ensemble) machine learning models when compared with the original DRASTIC approach. The newly designed multi-model ensemble-based approach can be considered as a pragmatic step for mapping groundwater contamination risks of multiple aquifer systems with multi-model techniques, yielding the high accuracy of the ANN committee-based model.

Keywords: DRASTIC; Groundwater contamination risk; Iran; Machine learning model; Multi-model.