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

• Published in: The Science of the total environment Vol. 621; pp. 697 - 712
• Main Authors: Barzegar, Rahim, Moghaddam, Asghar Asghari, Deo, Ravinesh, Fijani, Elham, Tziritis, Evangelos
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 15.04.2018
• Subjects: algorithms; aquifers; artificial intelligence; correlation; DRASTIC; groundwater; groundwater contamination; Groundwater contamination risk; Iran; Machine learning model; Multi-model; neural networks; nitrates; risk; Iran; Multi-model; Groundwater contamination risk; Iran; Machine learning model; DRASTIC
• ISSN: 0048-9697; 1879-1026; 1879-1026
• DOI: 10.1016/j.scitotenv.2017.11.185

•A DRASTIC vulnerability map, with an r of 0.64, was developed for a multiple aquifer system (e.g. unconfined, semi-confined and confined)•DRASTIC method was improved for mapping groundwater contamination risk (GCR) using ELM, SVR, M5 Tree and MARS algorithms•An ANN committee based multi-model, with an r of 0.88, was constructed to exploit individual model advantages•The subjectivity of the DRASTIC model was reduced based on the nature and hydrogeological features of the aquifers [Display omitted] 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.