Contents lists available at ScienceDirect Journal of Geochemical Exploration journal homepage: www.elsevier.com/locate/gexplo Predicting soil electrical conductivity using multi-layer perceptron integrated with grey wolf optimizer Amirhosein Mosavi a,b, ⁎ , Saeed Samadianfard c , Sabereh Darbandi c , Narjes Nabipour d, ⁎⁎ , Sultan Noman Qasem e,f , Ely Salwana g , Shahab S. Band d,h, ⁎⁎⁎ a Environmental Quality, Atmospheric Science and Climate Change Research Group, Ton Duc Thang University, Ho Chi Minh City, VietNam b Faculty of Environment and Labour Safety, Ton Duc Thang University, Ho Chi Minh City, VietNam c Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Tabriz, Iran d Institute of Research and Development, Duy Tan University, Da Nang 550000, VietNam e Computer Science Department, College of Computer and Information Sciences, Al Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi Arabia f Computer Science Department, Faculty of Applied Science, Taiz University, Taiz, Yemen g Institute of IR4.0, Universiti Kebangsaan Malaysia, Bangi 43600, Malaysia h Future Technology Research Center, College of Future, National Yunlin University of Science and Technology, 123 University Road, Section 3, Douliou, Yunlin 64002, Taiwan, ROC ARTICLE INFO Keywords: Artifcial neural network Grey wolf optimizer algorithm Hybrid predictive model Soil electrical conductivity Machine learning ABSTRACT In irrigation systems, salinity is a critical problem as it has undesirable impacts on crop health, agricultural throughput and farming management. Considering these, it is imperative to regularly monitor and develop measures to predict salinity of the soil to negate the salinization efects on agriculture. This paper constructs and evaluates the performance of the hybrid machine learning model of multilayer perceptron (MLP)-Grey Wolf Optimizer (MLP-GWO) for electrical conductivity (EC). MLP-GWO model is trained with soil sample data (i.e., parameters for organic matter, OM and soil constituents Ca +2 , Mg +2 , K + , Na + , Cl − , SO 4 −2 , HCO 3 − ) from Khuzestan province in Iran. Seven modelling scenarios representing diferent combinations of salinity para- meters are investigated to establish a hybrid MLP-GWO model that aims to reduce the error rate of the resulting forecasts of EC. To ascertain conclusive results, the MLP-GWO model is cross-validated with its classical coun- terpart without the add-in (i.e., GWO) optimizer, and the model error metrics are evaluated by coefcients of determination (R 2 ), root mean squared error (RMSE) and relative root mean square error (RRMSE) in in- dependent test data. For all tested predictive models, the performance of the MLP-GWO hybrid model is superior to a classical model, evidenced by larger R 2 (~0.552–0.711 relative to ~0.430–0.711) and a lower RMSE and RRSE (~1.293–3.537 vs. 1.616–4.421 and ~3.736–9.899 vs. 4.613–12.133). The proposed GWO as an optimizer leads to a plausible improvement in an MLP model due to the most optimal weights attained in the neuronal layer that facilitates a robust feature extraction process to predict EC. As conclusion, the obtained results proved the efectiveness of the hybrid MLP-GWI model for predicting soil properties, which has potential implications in precision agriculture where salinity needs to be modeled for crop management practices. 1. Introduction Soil salinization, known as the enrichment of the underlying soil with soluble salts, is one of the processes of land degradation, parti- cularly in arid locations. So, the evaporation of water from lower depths of the soil and small quantities of rainfall to leach down the salts from the root zones causes the accumulating of excessive soluble salts in soils (Gorji et al., 2015). Under such circumstances, soluble salts are gath- ered in the soil, impelling the soil properties with a signifcant weak- ening in productivity (Asfaw et al., 2018). According to the Food and https://doi.org/10.1016/j.gexplo.2020.106639 Received 14 April 2020; Received in revised form 5 August 2020; Accepted 1 September 2020 ⁎ Correspondence to: A. Mosavi, Environmental Quality, Atmospheric Science and Climate Change Research Group, Ton Duc Thang University, Ho Chi Minh City, Viet Nam. ⁎⁎ Corresponding author. ⁎⁎⁎ Correspondence to: S. S. Band, Institute of Research and Development, Duy Tan University, Da Nang 550000, Viet Nam. E-mail addresses: amirhosein.mosavi@tdtu.edu.vn (A. Mosavi), s.samadian@tabrizu.ac.ir (S. Samadianfard), sdarbandi@tabrizu.ac.ir (S. Darbandi), narjesnabipour@duytan.edu.vn (N. Nabipour), SNMohammed@imamu.edu.sa (S.N. Qasem), elysalwana@ukm.edu.my (E. Salwana), shamshirbands@yuntech.edu.tw, shamshirbandshahaboddin@duytan.edu.vn (S. S. Band). Journal of Geochemical Exploration 220 (2021) 106639 Available online 02 September 2020 0375-6742/ © 2020 Published by Elsevier B.V. T